From 6a5316440510ab729c555d4c1ae43fd89f6b0637 Mon Sep 17 00:00:00 2001
From: Ian Eyre <eyrei@aol.com>
Date: Sun, 19 Nov 2023 16:18:57 +0000
Subject: [PATCH 1/4] Updated Jupyter Notebook

---
 python-for-data-analysis/README.md            |  15 +
 python-for-data-analysis/Solution-New.ipynb   | 782 ++++++++++++++++++
 python-for-data-analysis/james_bond_data.csv  |  28 +
 python-for-data-analysis/james_bond_data.json |   1 +
 .../james_bond_data.parquet                   | Bin 0 -> 11050 bytes
 python-for-data-analysis/james_bond_data.xlsx | Bin 0 -> 11269 bytes
 .../james_bond_data_cleansed.csv              |  26 +
 7 files changed, 852 insertions(+)
 create mode 100644 python-for-data-analysis/README.md
 create mode 100644 python-for-data-analysis/Solution-New.ipynb
 create mode 100644 python-for-data-analysis/james_bond_data.csv
 create mode 100644 python-for-data-analysis/james_bond_data.json
 create mode 100644 python-for-data-analysis/james_bond_data.parquet
 create mode 100644 python-for-data-analysis/james_bond_data.xlsx
 create mode 100644 python-for-data-analysis/james_bond_data_cleansed.csv

diff --git a/python-for-data-analysis/README.md b/python-for-data-analysis/README.md
new file mode 100644
index 0000000000..8cb7b23c7f
--- /dev/null
+++ b/python-for-data-analysis/README.md
@@ -0,0 +1,15 @@
+# Downloadable Files
+
+This folder contains completed notebooks and other files used in the Real Python tutorial on [Using Python for Data Analysis](https://realpython.com/using-python-for-data-analysis/). 
+
+The `james_bond_data.csv` file contains the original uncleansed data and is the only mandatory file you will need to complete the tutorial. The same data is also available in JSON, Parquet and Excel versions to allow you to complete the optional exercises in reading from these file types.
+
+A cleansed version of the original data is available in the `james_bond_data_cleansed.csv` file.
+ 
+The complete code is available in the `Solution-New.ipynb` Jupyter notebook.
+
+## Setup
+
+The easiest way to work through this tutorial is to install and use [JupyterLab](https://realpython.com/using-jupyterlab/). Using Jupyter Notebook within JupyterLab will allow you to run code and see its results cleanly, and in the same way they are presented in the tutorial.  It will also make it easy for you to view the supporting files. 
+ 
+
diff --git a/python-for-data-analysis/Solution-New.ipynb b/python-for-data-analysis/Solution-New.ipynb
new file mode 100644
index 0000000000..6a361bcbc1
--- /dev/null
+++ b/python-for-data-analysis/Solution-New.ipynb
@@ -0,0 +1,782 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "ade4bd3f-543b-460b-980f-0b41aab2c8b6",
+   "metadata": {},
+   "source": [
+    "# Acquiring Your Data"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "83ad2114-5ed8-4a90-85fa-adea5eda4392",
+   "metadata": {},
+   "source": [
+    "## Reading Data From CSV Files"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a360772e-7829-4c15-9af9-d4596efc7351",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "! python -m pip install pandas"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2e52f486-232e-440b-8585-90416e4300c2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "\n",
+    "james_bond_data = pd.read_csv(\"james_bond_data.csv\").convert_dtypes()\n",
+    "james_bond_data.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e47c1f9b-b390-4035-956b-622615b57f32",
+   "metadata": {},
+   "source": [
+    "## Reading Data From Other Sources"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1d85aee9-cfeb-460b-9fe8-f3c7e7dfb764",
+   "metadata": {},
+   "source": [
+    "### Reading JSON"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7465cd11-dad4-4741-9372-f825b28c33d6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "\n",
+    "james_bond_data_json = pd.read_json(\"james_bond_data.json\").convert_dtypes()\n",
+    "james_bond_data_json.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "47a0e4a6-0ed9-4253-9833-0ad22c49b968",
+   "metadata": {},
+   "source": [
+    "### Reading Excel"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a0364b81-64a0-4098-89fc-e58bd6d68257",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "! python -m pip install openpyxl"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8302139f-52dc-4f95-aa9a-96040ae5d82b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import openpyxl\n",
+    "import pandas as pd\n",
+    "\n",
+    "james_bond_data_excel = pd.read_excel(\"james_bond_data.xlsx\").convert_dtypes()\n",
+    "james_bond_data_excel.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8b3237b8-99a0-4070-81a9-e7f9e44c8973",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "! python.exe -m pip install --upgrade pip"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "be4a1143-c966-4056-8a5e-3bdebe2a9b1f",
+   "metadata": {},
+   "source": [
+    "### Reading Parquet"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f36ef600-e6ba-4cc6-9ee3-0cbf369a4be2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!python -m pip install pyarrow"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c86284a2-9073-4240-b4d5-5e8b0373fc27",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "james_bond_data_parquet = pd.read_parquet(\n",
+    "    \"james_bond_data.parquet\"\n",
+    ").convert_dtypes()\n",
+    "james_bond_data_parquet.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "69f884c2-92e8-4db3-bd63-84007f654808",
+   "metadata": {},
+   "source": [
+    "### Scraping HTML"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b902722d-9648-4124-80b0-64004342170d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!python -m pip install lxml"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1fb2ff9c-3030-4f4a-be30-c2ab68452a21",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "james_bond_data_html = pd.read_html(\n",
+    "    \"https://en.wikipedia.org/wiki/List_of_James_Bond_novels_and_short_stories\"\n",
+    ")\n",
+    "james_bond_data_html = james_bond_data_html[1].convert_dtypes()\n",
+    "james_bond_data_html.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "31068de2-9864-434a-9652-b115d1131684",
+   "metadata": {},
+   "source": [
+    "# Cleansing Your Data With Python"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e432b28e-257b-422b-b2f8-06f41608391b",
+   "metadata": {},
+   "source": [
+    "## Dealing With Missing Data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "38eb1abb-9f89-4a53-9e77-f7c71dbeff18",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "james_bond_data.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b29d5a34-c930-4ce2-898c-b9e8aa7f771d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "james_bond_data[james_bond_data.isna().any(axis=\"columns\")]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1db9201a-11c1-4cdd-9625-d70cee736191",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = james_bond_data.combine_first(\n",
+    "    pd.DataFrame({\"Avg_User_IMDB\": {10: 7.1}, \"Avg_User_Rtn_Tom\": {10: 6.8}})\n",
+    ")\n",
+    "\n",
+    "data"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f6297c81-4c63-4eff-95e3-4a944bb5fe03",
+   "metadata": {},
+   "source": [
+    "## Correcting Invalid Data Types"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "001996e3-2fce-4228-a873-b78eef613bba",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data[[\"US_Gross\", \"World_Gross\", \"Budget ($ 000s)\", \"Film_Length\"]].head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "880e4710-1c11-4de2-a2c3-97a9672ce6f7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = james_bond_data.combine_first(\n",
+    "    pd.DataFrame({\"Avg_User_IMDB\": {10: 7.1}, \"Avg_User_Rtn_Tom\": {10: 6.8}})\n",
+    ").assign(\n",
+    "    US_Gross=lambda data: (\n",
+    "        data[\"US_Gross\"].replace(\"[$,]\", \"\", regex=True).astype(float)\n",
+    "    ),\n",
+    "    World_Gross=lambda data: (\n",
+    "        data[\"World_Gross\"].replace(\"[$,]\", \"\", regex=True).astype(float)\n",
+    "    ),\n",
+    "    Budget=lambda data: (\n",
+    "        data[\"Budget ($ 000s)\"].replace(\"[$,]\", \"\", regex=True).astype(float)\n",
+    "    ),\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a542149d-35d1-4012-8638-25e59f2f3ae4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data[[\"US_Gross\", \"World_Gross\", \"Budget\"]].head()\n",
+    "data[[\"US_Gross\", \"World_Gross\", \"Budget\"]].info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ae9c1d1b-a620-43c5-a199-eb6a7bff7ce2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = james_bond_data.combine_first(\n",
+    "    pd.DataFrame({\"Avg_User_IMDB\": {10: 7.1}, \"Avg_User_Rtn_Tom\": {10: 6.8}})\n",
+    ").assign(\n",
+    "    US_Gross=lambda data: (\n",
+    "        data[\"US_Gross\"].replace(\"[$,]\", \"\", regex=True).astype(float)\n",
+    "    ),\n",
+    "    World_Gross=lambda data: (\n",
+    "        data[\"World_Gross\"].replace(\"[$,]\", \"\", regex=True).astype(float)\n",
+    "    ),\n",
+    "    Budget=lambda data: (\n",
+    "        data[\"Budget ($ 000s)\"].replace(\"[$,]\", \"\", regex=True).astype(float)\n",
+    "    ),\n",
+    "    Film_Length=lambda data: (\n",
+    "        data[\"Film_Length\"].str.rstrip(\"mins\").astype(int)\n",
+    "    ),\n",
+    ")\n",
+    "\n",
+    "data[[\"Film_Length\"]].head()\n",
+    "data[[\"Film_Length\"]].info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ed0ead0e-7310-4c82-86d5-2480a95f1525",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = james_bond_data.combine_first(\n",
+    "    pd.DataFrame({\"Avg_User_IMDB\": {10: 7.1}, \"Avg_User_Rtn_Tom\": {10: 6.8}})\n",
+    ").assign(\n",
+    "    US_Gross=lambda data: (\n",
+    "        data[\"US_Gross\"].replace(\"[$,]\", \"\", regex=True).astype(float)\n",
+    "    ),\n",
+    "    World_Gross=lambda data: (\n",
+    "        data[\"World_Gross\"].replace(\"[$,]\", \"\", regex=True).astype(float)\n",
+    "    ),\n",
+    "    Budget=lambda data: (\n",
+    "        data[\"Budget ($ 000s)\"].replace(\"[$,]\", \"\", regex=True).astype(float)\n",
+    "    ),\n",
+    "    Film_Length=lambda data: (\n",
+    "        data[\"Film_Length\"].str.rstrip(\"mins\").astype(int)\n",
+    "    ),\n",
+    "    Release=lambda data: pd.to_datetime(data[\"Release\"], format=\"%B, %Y\"),\n",
+    "    Release_Year=lambda data: data[\"Release\"].dt.year,\n",
+    ")\n",
+    "\n",
+    "data[[\"Release\"]].info()\n",
+    "data[[\"Release_Year\"]].head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "89653d81-3bcd-4078-83cb-ad4b2fa560e6",
+   "metadata": {},
+   "source": [
+    "## Fixing Inconsistencies in Data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "bc483320-7895-4368-a672-b98f8d0c9755",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = james_bond_data.combine_first(\n",
+    "    pd.DataFrame({\"Avg_User_IMDB\": {10: 7.1}, \"Avg_User_Rtn_Tom\": {10: 6.8}})\n",
+    ").assign(\n",
+    "    US_Gross=lambda data: (\n",
+    "        data[\"US_Gross\"].replace(\"[$,]\", \"\", regex=True).astype(float)\n",
+    "    ),\n",
+    "    World_Gross=lambda data: (\n",
+    "        data[\"World_Gross\"].replace(\"[$,]\", \"\", regex=True).astype(float)\n",
+    "    ),\n",
+    "    Budget=lambda data: (\n",
+    "        data[\"Budget ($ 000s)\"].replace(\"[$,]\", \"\", regex=True).astype(float)\n",
+    "        * 1000\n",
+    "    ),\n",
+    "    Film_Length=lambda data: (\n",
+    "        data[\"Film_Length\"].str.rstrip(\"mins\").astype(int)\n",
+    "    ),\n",
+    "    Release=lambda data: pd.to_datetime(data[\"Release\"], format=\"%B, %Y\"),\n",
+    "    Release_Year=lambda data: data[\"Release\"].dt.year,\n",
+    ")\n",
+    "\n",
+    "data[[\"US_Gross\", \"World_Gross\", \"Budget\"]].head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3e129b32-5e66-41cb-b938-8fd58bb94116",
+   "metadata": {},
+   "source": [
+    "## Removing Duplicate Data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "be7aad8b-ef3f-48a6-a9a0-de909133921f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data[\"Movie\"].value_counts().head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "20067efb-e7c7-4690-b483-1d29847ad24f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "duplicate_movies = [\"The Man with the Golden Gun\", \"The Living Daylights\"]\n",
+    "data[data[\"Movie\"].isin(duplicate_movies)]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c98c7640-1472-4869-9fdd-f070d665ae1d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = james_bond_data.combine_first(\n",
+    "    pd.DataFrame({\"Avg_User_IMDB\": {10: 7.1}, \"Avg_User_Rtn_Tom\": {10: 6.8}})\n",
+    ").assign(\n",
+    "    US_Gross=lambda data: (\n",
+    "        data[\"US_Gross\"].replace(\"[$,]\", \"\", regex=True).astype(float)\n",
+    "    ),\n",
+    "    World_Gross=lambda data: (\n",
+    "        data[\"World_Gross\"].replace(\"[$,]\", \"\", regex=True).astype(float)\n",
+    "    ),\n",
+    "    Budget=lambda data: (\n",
+    "        data[\"Budget ($ 000s)\"].replace(\"[$,]\", \"\", regex=True).astype(float)\n",
+    "    ),\n",
+    "    Film_Length=lambda data: (data[\"Film_Length\"].str.rstrip(\"mins\").astype(int)),\n",
+    "    Release=lambda data: pd.to_datetime(data[\"Release\"], format=\"%B, %Y\"),\n",
+    "    Release_Year=lambda data: data[\"Release\"].dt.year\n",
+    ").drop_duplicates(ignore_index=True)\n",
+    "\n",
+    "duplicate_movies = [\"The Man with the Golden Gun\", \"The Living Daylights\"]\n",
+    "data[data[\"Movie\"].isin(duplicate_movies)]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8bdaa8b1-9f2e-46a5-b53a-c1ae4c201c99",
+   "metadata": {},
+   "source": [
+    "## Correcting Spelling Errors"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e442e51a-28fd-42d7-94b0-aaf1abe5d9a8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data[\"Bond\"].value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f9863aa7-b5db-4ab1-be63-727ff437b63b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = (\n",
+    "    james_bond_data.combine_first(\n",
+    "        pd.DataFrame(\n",
+    "            {\"Avg_User_IMDB\": {10: 7.1}, \"Avg_User_Rtn_Tom\": {10: 6.8}}\n",
+    "        )\n",
+    "    )\n",
+    "    .assign(\n",
+    "        US_Gross=lambda data: (\n",
+    "            data[\"US_Gross\"].replace(\"[$,]\", \"\", regex=True).astype(float)\n",
+    "        ),\n",
+    "        World_Gross=lambda data: (\n",
+    "            data[\"World_Gross\"].replace(\"[$,]\", \"\", regex=True).astype(float)\n",
+    "        ),\n",
+    "        Budget=lambda data: (\n",
+    "            data[\"Budget ($ 000s)\"]\n",
+    "            .replace(\"[$,]\", \"\", regex=True)\n",
+    "            .astype(float)\n",
+    "        ),\n",
+    "        Film_Length=lambda data: (\n",
+    "            data[\"Film_Length\"].str.rstrip(\"mins\").astype(int)\n",
+    "        ),\n",
+    "        Release=lambda data: pd.to_datetime(data[\"Release\"], format=\"%B, %Y\"),\n",
+    "        Release_Year=lambda data: data[\"Release\"].dt.year,\n",
+    "        Bond=lambda data: (\n",
+    "            data[\"Bond\"]\n",
+    "            .str.replace(\"Shawn\", \"Sean\")\n",
+    "            .str.replace(\"MOORE\", \"Moore\")\n",
+    "        ),\n",
+    "    )\n",
+    "    .drop_duplicates(ignore_index=True)\n",
+    ")\n",
+    "\n",
+    "data[\"Bond\"].value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a26b138d-72e5-4e15-a875-ee65023545d1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "james_bond_data[\"Bond_Car_MFG\"].value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fd4ae142-e339-4601-b0a4-84375eb28c02",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = (\n",
+    "    james_bond_data.combine_first(\n",
+    "        pd.DataFrame(\n",
+    "            {\"Avg_User_IMDB\": {10: 7.1}, \"Avg_User_Rtn_Tom\": {10: 6.8}}\n",
+    "        )\n",
+    "    )\n",
+    "    .assign(\n",
+    "        US_Gross=lambda data: (\n",
+    "            data[\"US_Gross\"].replace(\"[$,]\", \"\", regex=True).astype(float)\n",
+    "        ),\n",
+    "        World_Gross=lambda data: (\n",
+    "            data[\"World_Gross\"].replace(\"[$,]\", \"\", regex=True).astype(float)\n",
+    "        ),\n",
+    "        Budget=lambda data: (\n",
+    "            data[\"Budget ($ 000s)\"]\n",
+    "            .replace(\"[$,]\", \"\", regex=True)\n",
+    "            .astype(float)\n",
+    "        ),\n",
+    "        Film_Length=lambda data: (\n",
+    "            data[\"Film_Length\"].str.rstrip(\"mins\").astype(int)\n",
+    "        ),\n",
+    "        Release=lambda data: pd.to_datetime(data[\"Release\"], format=\"%B, %Y\"),\n",
+    "        Release_Year=lambda data: data[\"Release\"].dt.year,\n",
+    "        Bond=lambda data: (\n",
+    "            data[\"Bond\"]\n",
+    "            .str.replace(\"Shawn\", \"Sean\")\n",
+    "            .str.replace(\"MOORE\", \"Moore\")\n",
+    "        ),\n",
+    "        Bond_Car_MFG=lambda data: data[\"Bond_Car_MFG\"].str.replace(\n",
+    "            \"Astin\", \"Aston\"\n",
+    "        ),\n",
+    "    )\n",
+    "    .drop_duplicates(ignore_index=True)\n",
+    ")\n",
+    "\n",
+    "data[\"Bond_Car_MFG\"].value_counts()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "50c80bc8-fdb9-4c28-af5a-cd6b66c7a01d",
+   "metadata": {},
+   "source": [
+    "## Checking For Invalid Outliers"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8260f6b1-6d7f-4338-95b7-8946d69a92e2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data[[\"Film_Length\", \"Martinis\"]].describe()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c73fe06b-5f42-4357-9b0f-2e460bf0dacf",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = (\n",
+    "    james_bond_data.combine_first(\n",
+    "        pd.DataFrame(\n",
+    "            {\"Avg_User_IMDB\": {10: 7.1}, \"Avg_User_Rtn_Tom\": {10: 6.8}}\n",
+    "        )\n",
+    "    )\n",
+    "    .assign(\n",
+    "        US_Gross=lambda data: (\n",
+    "            data[\"US_Gross\"].replace(\"[$,]\", \"\", regex=True).astype(float)\n",
+    "        ),\n",
+    "        World_Gross=lambda data: (\n",
+    "            data[\"World_Gross\"].replace(\"[$,]\", \"\", regex=True).astype(float)\n",
+    "        ),\n",
+    "        Budget=lambda data: (\n",
+    "            data[\"Budget ($ 000s)\"]\n",
+    "            .replace(\"[$,]\", \"\", regex=True)\n",
+    "            .astype(float)\n",
+    "        ),\n",
+    "        Film_Length=lambda data: (\n",
+    "            data[\"Film_Length\"]\n",
+    "            .str.rstrip(\"mins\")\n",
+    "            .astype(int)\n",
+    "            .replace(1200, 120)\n",
+    "        ),\n",
+    "        Release=lambda data: pd.to_datetime(data[\"Release\"], format=\"%B, %Y\"),\n",
+    "        Release_Year=lambda data: data[\"Release\"].dt.year,\n",
+    "        Bond=lambda data: (\n",
+    "            data[\"Bond\"]\n",
+    "            .str.replace(\"Shawn\", \"Sean\")\n",
+    "            .str.replace(\"MOORE\", \"Moore\")\n",
+    "        ),\n",
+    "        Bond_Car_MFG=lambda data: data[\"Bond_Car_MFG\"].str.replace(\n",
+    "            \"Astin\", \"Aston\"\n",
+    "        ),\n",
+    "        Martinis=lambda data: data[\"Martinis\"].replace(-6, 6),\n",
+    "    )\n",
+    "    .drop_duplicates(ignore_index=True)\n",
+    ")\n",
+    "\n",
+    "data[[\"Film_Length\", \"Martinis\"]].describe()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "52db1351-36ed-4104-a999-345ebbc62214",
+   "metadata": {},
+   "source": [
+    "## Storing Your Cleansed Data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "575a774e-6913-41fb-8ff9-4d786f478007",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data.to_csv(\"james_bond_data_cleansed.csv\", index=False)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f50918ee-e61f-46b2-b0c2-1ffa2c62bbc0",
+   "metadata": {},
+   "source": [
+    "# Using Python for Data Analysis"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "86817f68-05a0-4235-a1c8-a5d1f6e9141e",
+   "metadata": {},
+   "source": [
+    "## Performing a Regression Analysis"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "bee6d6cb-e418-4c1d-8b75-604b9ab2e63d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!python -m pip install matplotlib scikit-learn"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "27d0a3dd-e71a-4b8a-883c-40cb5c001f7e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "data = pd.read_csv(\"james_bond_data_cleansed.csv\").convert_dtypes()\n",
+    "\n",
+    "fig, ax = plt.subplots()\n",
+    "ax.scatter(data[\"Avg_User_IMDB\"], data[\"Avg_User_Rtn_Tom\"])\n",
+    "ax.set_title(\"Scatter Plot of Ratings\")\n",
+    "ax.set_xlabel(\"Average IMDB Rating\")\n",
+    "ax.set_ylabel(\"Average Rotten Tomatoes Rating\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "669fb9d7-d744-4e6b-899e-a69aebec53ed",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.linear_model import LinearRegression\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "x = data.loc[:, [\"Avg_User_IMDB\"]]\n",
+    "y = data.loc[:, \"Avg_User_Rtn_Tom\"]\n",
+    "\n",
+    "model = LinearRegression()\n",
+    "model.fit(x, y)\n",
+    "\n",
+    "r_squared = f\"R-Squared: {model.score(x, y):.2f}\"\n",
+    "best_fit = f\"y = {model.coef_[0]:.4f}x{model.intercept_:+.4f}\"\n",
+    "y_pred = model.predict(x)\n",
+    "\n",
+    "fig, ax = plt.subplots()\n",
+    "ax.scatter(x, y)\n",
+    "ax.plot(x, y_pred, color=\"red\")\n",
+    "ax.text(7.25, 5.5, r_squared, fontsize=10)\n",
+    "ax.text(7.25, 7, best_fit, fontsize=10)\n",
+    "ax.set_title(\"Scatter Plot of Ratings\")\n",
+    "ax.set_xlabel(\"Average IMDB Rating\")\n",
+    "ax.set_ylabel(\"Average Rotten Tomatoes Rating\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b38df412-c320-49fb-93ae-e253405537a8",
+   "metadata": {},
+   "source": [
+    "## Investigating a Statistical Distribution"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "938e5942-e57f-4e41-99f1-215cfb37d0df",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [],
+   "source": [
+    "length = data[\"Film_Length\"].value_counts(bins=7).sort_index()\n",
+    "length.plot.bar(\n",
+    "    title=\"Film Length Distribution\", xlabel=\"Time Range (mins)\", ylabel=\"Count\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ff4e9955-baf4-48eb-b032-fbf55f439194",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data[\"Film_Length\"].agg([\"mean\", \"max\", \"min\", \"std\"])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1b14c433-c3a6-4484-bc0a-26825bd1e870",
+   "metadata": {},
+   "source": [
+    "## Finding No Relationship"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2bb83374-347f-4cf6-bc21-8180a003371d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "fig, ax = plt.subplots()\n",
+    "ax.scatter(data[\"Avg_User_IMDB\"], data[\"Kills_Bond\"])\n",
+    "ax.set_title(\"Scatter Plot of Kills vs Ratings\")\n",
+    "ax.set_xlabel(\"Average IMDB Rating\")\n",
+    "ax.set_ylabel(\"Kills by Bond\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.0"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/python-for-data-analysis/james_bond_data.csv b/python-for-data-analysis/james_bond_data.csv
new file mode 100644
index 0000000000..d8b675dddd
--- /dev/null
+++ b/python-for-data-analysis/james_bond_data.csv
@@ -0,0 +1,28 @@
+Release,Movie,Bond,Bond_Car_MFG,US_Gross,World_Gross,Budget ($ 000s),Film_Length,Avg_User_IMDB,Avg_User_Rtn_Tom,Martinis,Kills_Bond
+"June, 1962",Dr. No,Sean Connery,Sunbeam," $16,067,035.00 "," $59,567,035.00 "," $1,000.00 ",110 mins,7.3,7.7,2,4
+"August, 1963",From Russia with Love,Sean Connery,Bently," $24,800,000.00 "," $78,900,000.00 "," $2,000.00 ",115 mins,7.5,8,0,11
+"May, 1964",Goldfinger,Sean Connery,Aston Martin," $51,100,000.00 "," $124,900,000.00 "," $3,000.00 ",110 mins,7.8,8.4,1,9
+"September, 1965",Thunderball,Sean Connery,Aston Martin," $63,600,000.00 "," $141,200,000.00 "," $9,000.00 ",130 mins,7,6.8,0,20
+"November, 1967",You Only Live Twice,Sean Connery,Toyota," $43,100,000.00 "," $111,600,000.00 "," $9,500.00 ",117 mins,6.9,6.3,1,21
+"July, 1969",On Her Majesty's Secret Service,George Lazenby,Mercury," $22,800,000.00 "," $82,000,000.00 "," $8,000.00 ",142 mins,6.8,6.7,1,5
+"March, 1971",Diamonds Are Forever,Shawn Connery,Ford," $43,800,000.00 "," $116,000,000.00 "," $7,200.00 ",1200 mins,6.7,6.3,0,7
+"August, 1973",Live and Let Die,Roger Moore,AMC," $35,400,000.00 "," $161,800,000.00 "," $7,000.00 ",121 mins,6.8,5.9,0,8
+"July, 1974",The Man with the Golden Gun,Roger Moore,AMC," $21,000,000.00 "," $97,600,000.00 "," $7,000.00 ",125 mins,6.7,5.1,0,1
+"July, 1974",The Man with the Golden Gun,Roger Moore,AMC," $21,000,000.00 "," $97,600,000.00 "," $7,000.00 ",125 mins,6.7,5.1,0,1
+"April, 1977",The Spy Who Loved Me,Roger Moore,Lotus," $46,800,000.00 "," $185,400,000.00 "," $14,000.00 ",125 mins,,,1,31
+"October, 1979",Moonraker,Roger Moore,Lotus," $70,300,000.00 "," $210,300,000.00 "," $31,000.00 ",126 mins,6.2,5.7,1,12
+"June, 1981",For Your Eyes Only,Roger MOORE,Citroen," $54,800,000.00 "," $195,300,000.00 "," $28,000.00 ",127 mins,6.8,6.3,0,18
+"March, 1983",Octopussy,Roger Moore,Bajaj," $67,900,000.00 "," $187,500,000.00 "," $27,500.00 ",131 mins,6.5,5.3,0,15
+"October, 1985",A View to a Kill,Roger Moore,Rolls Royce," $50,327,960.00 "," $152,627,960.00 "," $30,000.00 ",131 mins,6.2,4.7,0,5
+"May, 1987",The Living Daylights,Timothy Dalton,Rolls Royce," $51,185,000.00 "," $191,200,000.00 "," $40,000.00 ",130 mins,6.7,6.3,2,13
+"May, 1987",The Living Daylights,Timothy Dalton,Rolls Royce," $51,185,000.00 "," $191,200,000.00 "," $40,000.00 ",130 mins,6.7,6.3,2,13
+"January, 1989",License to Kill,Timothy Dalton,Aston Martin," $34,667,015.00 "," $156,167,015.00 "," $42,000.00 ",133 mins,6.5,6,1,10
+"September, 1995",GoldenEye,Pierce Brosnan,BMW," $106,429,941.00 "," $356,429,941.00 "," $60,000.00 ",130 mins,7.2,6.9,1,47
+"July, 1997",Tomorrow Never Dies,Pierce Brosnan,Aston Martin," $125,304,276.00 "," $339,504,276.00 "," $110,000.00 ",119 mins,6.4,6,1,30
+"June, 1999",The World Is Not Enough,Pierce Brosnan,BMW," $126,930,660.00 "," $361,730,660.00 "," $135,000.00 ",128 mins,6.3,5.7,1,27
+"August, 2002",Die Another Day,Pierce Brosnan,Aston Martin," $160,942,139.00 "," $431,942,139.00 "," $142,000.00 ",133 mins,6,6.1,2,31
+"February, 2006",Casino Royale,Daniel Craig,Astin Martin," $167,365,000.00 "," $596,365,000.00 "," $102,000.00 ",144 mins,7.9,7.8,3,11
+"December, 2008",Quantum of Solace,Daniel Craig,Aston Martin," $169,368,427.00 "," $591,692,078.00 "," $230,000.00 ",106 mins,6.7,6.1,-6,16
+"November, 2012",Skyfall,Daniel Craig,Astin Martin," $304,360,277.00 "," $1,108,561,108.00 "," $200,000.00 ",143 mins,7.8,8.2,1,26
+"September, 2015",Spectre,Daniel Craig,Aston Martin," $200,074,175.00 "," $879,620,923.00 "," $245,000.00 ",148 mins,6.8,6.4,1,30
+"November, 2021",No Time to Die,Daniel Craig,Aston Martin," $160,891,007.00 "," $759,959,662.00 "," $275,000.00 ",163 mins,7.3,7.3,1,14
diff --git a/python-for-data-analysis/james_bond_data.json b/python-for-data-analysis/james_bond_data.json
new file mode 100644
index 0000000000..852810b38e
--- /dev/null
+++ b/python-for-data-analysis/james_bond_data.json
@@ -0,0 +1 @@
+{"Release":{"0":"June, 1962","1":"August, 1963","2":"May, 1964","3":"September, 1965","4":"November, 1967","5":"July, 1969","6":"March, 1971","7":"August, 1973","8":"July, 1974","9":"July, 1974","10":"April, 1977","11":"October, 1979","12":"June, 1981","13":"March, 1983","14":"October, 1985","15":"May, 1987","16":"May, 1987","17":"January, 1989","18":"September, 1995","19":"July, 1997","20":"June, 1999","21":"August, 2002","22":"February, 2006","23":"December, 2008","24":"November, 2012","25":"September, 2015","26":"November, 2021"},"Movie":{"0":"Dr. No","1":"From Russia with Love","2":"Goldfinger","3":"Thunderball","4":"You Only Live Twice","5":"On Her Majesty's Secret Service","6":"Diamonds Are Forever","7":"Live and Let Die","8":"The Man with the Golden Gun","9":"The Man with the Golden Gun","10":"The Spy Who Loved Me","11":"Moonraker","12":"For Your Eyes Only","13":"Octopussy","14":"A View to a Kill","15":"The Living Daylights","16":"The Living Daylights","17":"License to Kill","18":"GoldenEye","19":"Tomorrow Never Dies","20":"The World Is Not Enough","21":"Die Another Day","22":"Casino Royale","23":"Quantum of Solace","24":"Skyfall","25":"Spectre","26":"No Time to Die"},"Bond":{"0":"Sean Connery","1":"Sean Connery","2":"Sean Connery","3":"Sean Connery","4":"Sean Connery","5":"George Lazenby","6":"Shawn Connery","7":"Roger Moore","8":"Roger Moore","9":"Roger Moore","10":"Roger Moore","11":"Roger Moore","12":"Roger MOORE","13":"Roger Moore","14":"Roger Moore","15":"Timothy Dalton","16":"Timothy Dalton","17":"Timothy Dalton","18":"Pierce Brosnan","19":"Pierce Brosnan","20":"Pierce Brosnan","21":"Pierce Brosnan","22":"Daniel Craig","23":"Daniel Craig","24":"Daniel Craig","25":"Daniel Craig","26":"Daniel Craig"},"Bond_Car_MFG":{"0":"Sunbeam","1":"Bently","2":"Aston Martin","3":"Aston Martin","4":"Toyota","5":"Mercury","6":"Ford","7":"AMC","8":"AMC","9":"AMC","10":"Lotus","11":"Lotus","12":"Citroen","13":"Bajaj","14":"Rolls Royce","15":"Rolls Royce","16":"Rolls Royce","17":"Aston Martin","18":"BMW","19":"Aston Martin","20":"BMW","21":"Aston Martin","22":"Astin Martin","23":"Aston Martin","24":"Astin Martin","25":"Aston Martin","26":"Aston Martin"},"US_Gross":{"0":" $16,067,035.00 ","1":" $24,800,000.00 ","2":" $51,100,000.00 ","3":" $63,600,000.00 ","4":" $43,100,000.00 ","5":" $22,800,000.00 ","6":" $43,800,000.00 ","7":" $35,400,000.00 ","8":" $21,000,000.00 ","9":" $21,000,000.00 ","10":" $46,800,000.00 ","11":" $70,300,000.00 ","12":" $54,800,000.00 ","13":" $67,900,000.00 ","14":" $50,327,960.00 ","15":" $51,185,000.00 ","16":" $51,185,000.00 ","17":" $34,667,015.00 ","18":" $106,429,941.00 ","19":" $125,304,276.00 ","20":" $126,930,660.00 ","21":" $160,942,139.00 ","22":" $167,365,000.00 ","23":" $169,368,427.00 ","24":" $304,360,277.00 ","25":" $200,074,175.00 ","26":" $160,891,007.00 "},"World_Gross":{"0":" $59,567,035.00 ","1":" $78,900,000.00 ","2":" $124,900,000.00 ","3":" $141,200,000.00 ","4":" $111,600,000.00 ","5":" $82,000,000.00 ","6":" $116,000,000.00 ","7":" $161,800,000.00 ","8":" $97,600,000.00 ","9":" $97,600,000.00 ","10":" $185,400,000.00 ","11":" $210,300,000.00 ","12":" $195,300,000.00 ","13":" $187,500,000.00 ","14":" $152,627,960.00 ","15":" $191,200,000.00 ","16":" $191,200,000.00 ","17":" $156,167,015.00 ","18":" $356,429,941.00 ","19":" $339,504,276.00 ","20":" $361,730,660.00 ","21":" $431,942,139.00 ","22":" $596,365,000.00 ","23":" $591,692,078.00 ","24":" $1,108,561,108.00 ","25":" $879,620,923.00 ","26":" $759,959,662.00 "},"Budget ($ 000s)":{"0":" $1,000.00 ","1":" $2,000.00 ","2":" $3,000.00 ","3":" $9,000.00 ","4":" $9,500.00 ","5":" $8,000.00 ","6":" $7,200.00 ","7":" $7,000.00 ","8":" $7,000.00 ","9":" $7,000.00 ","10":" $14,000.00 ","11":" $31,000.00 ","12":" $28,000.00 ","13":" $27,500.00 ","14":" $30,000.00 ","15":" $40,000.00 ","16":" $40,000.00 ","17":" $42,000.00 ","18":" $60,000.00 ","19":" $110,000.00 ","20":" $135,000.00 ","21":" $142,000.00 ","22":" $102,000.00 ","23":" $230,000.00 ","24":" $200,000.00 ","25":" $245,000.00 ","26":" $275,000.00 "},"Film_Length":{"0":"110 mins","1":"115 mins","2":"110 mins","3":"130 mins","4":"117 mins","5":"142 mins","6":"1200 mins","7":"121 mins","8":"125 mins","9":"125 mins","10":"125 mins","11":"126 mins","12":"127 mins","13":"131 mins","14":"131 mins","15":"130 mins","16":"130 mins","17":"133 mins","18":"130 mins","19":"119 mins","20":"128 mins","21":"133 mins","22":"144 mins","23":"106 mins","24":"143 mins","25":"148 mins","26":"163 mins"},"Avg_User_IMDB":{"0":7.3,"1":7.5,"2":7.8,"3":7.0,"4":6.9,"5":6.8,"6":6.7,"7":6.8,"8":6.7,"9":6.7,"10":null,"11":6.2,"12":6.8,"13":6.5,"14":6.2,"15":6.7,"16":6.7,"17":6.5,"18":7.2,"19":6.4,"20":6.3,"21":6.0,"22":7.9,"23":6.7,"24":7.8,"25":6.8,"26":7.3},"Avg_User_Rtn_Tom":{"0":7.7,"1":8.0,"2":8.4,"3":6.8,"4":6.3,"5":6.7,"6":6.3,"7":5.9,"8":5.1,"9":5.1,"10":null,"11":5.7,"12":6.3,"13":5.3,"14":4.7,"15":6.3,"16":6.3,"17":6.0,"18":6.9,"19":6.0,"20":5.7,"21":6.1,"22":7.8,"23":6.1,"24":8.2,"25":6.4,"26":7.3},"Martinis":{"0":2,"1":0,"2":1,"3":0,"4":1,"5":1,"6":0,"7":0,"8":0,"9":0,"10":1,"11":1,"12":0,"13":0,"14":0,"15":2,"16":2,"17":1,"18":1,"19":1,"20":1,"21":2,"22":3,"23":-6,"24":1,"25":1,"26":1},"Kills_Bond":{"0":4,"1":11,"2":9,"3":20,"4":21,"5":5,"6":7,"7":8,"8":1,"9":1,"10":31,"11":12,"12":18,"13":15,"14":5,"15":13,"16":13,"17":10,"18":47,"19":30,"20":27,"21":31,"22":11,"23":16,"24":26,"25":30,"26":14}}
\ No newline at end of file
diff --git a/python-for-data-analysis/james_bond_data.parquet b/python-for-data-analysis/james_bond_data.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..88bd22b4fb36adc606eaf6eacd5b46d56121e5d1
GIT binary patch
literal 11050
zcmcgyZEPDydY+Y*HffWwBx@DYk?cK1W)x>7?FYZsa9k}Zks?D%7A29CF0HU6R}`h?
zE{`9Q=rl!8^om?AIQRnR;5!tDG{}#jz4S+s25s6O*Zw#J2M6en^iZHd5geLJa43qP
zD1stro4zxoBub?6f!HQIyEE_1ydTdy^Ugaf-%yeQLo=_QVt(5jXG8`KAoRoDr_UgS
zVs%5~SV8uQc4#T}LcLnE^bJckXeHE!#o_UsgX)r2u4$#LR<WEP_C5rJd2`1#fc&-_
zNViF}eAY5;t>iYTDcUdi))DQOCMV$Op(gs2a;2zSCRo1%rY+=ZrlUmrW!t3f&*^|b
zO`=5qx9Na%brR75@5tYxfF(W{Q;oV>vHX}0$icgamc6!h+uKNXykjfTvOM`W$S(4{
zNd31xtYs^<McndH1J)TWH*p3x0@Q#!3>87VT1QrRUsWh*iUNa}0CSCFd`us6ia9mx
zL*wTTOygJ>>2;nZ3S&(Ce$aSW?}4X}ve?+?l^0~|<-f{Q|Ksn+AA94|EYRI=T80_B
z%ZpC+xtynyny#r;jp-Tk4SjHW=w}x9OSIei<x*T6cn2{(2p)a#LI~Rbe46=_)BE1~
z_ufxlJ_Yod$|O5)GEfUw%o3ZdSF1&p-7VHO*|@o*VUI>kJ-<;j3R>kXw3avPMqaCA
zRb4+1%~i9`E*N@)jTd(`c6qm$(=Gvd!C>dK3Y$>3v}&#KSe0GUauuxxugVS#8H6D-
zMYUua`6{baG&XEjv>mO|2Xsr6SB*RyhtV@d?GZ%P`!rx=*zVYCn;J{qc4`J2sT+fi
zOU|WogH3OmmbYf|Y(gVT%ruRPx~)|Ps1G=^!h(JkcDA8aEpJkfmhoySgNY3+NMTb&
zZI`W?tja!B)b;+SH^B%nl$}u<da<xstKyX!2YrpIMomypP;uMKo4^bkzHFAvO2yn|
z=dt2g)#}64!^@yy+N|h#Hd+N-YwWCH)(e|d5)WV%!>qxQ{$xRI;I$i4t3|_PlV(HJ
zwSFKh)>WfcFR|tZyJYHWPCE_6rR~NBfK94pEmx~(&F#W27fTw}9yoVdhUdF@#@Tn=
zX5jxN>+!vFhwIUjFn2&0UX8EYhCZ>nUwO#=Z)DMbMQL5v<qJK`CsZ8PDUKrFrC!Hz
zV@XpDHe?!xR%u{!Bbr$$Xlz`)sTo-U-qNPJYxF-Fz-uyT!s28TCM=?nbM}RW<SeCl
z03JZQ0nXHGra=vOZWOgjPGf@=vudaYRp(|@qp0a@sG=4NfZ#a89ofha9p&J(w~q&@
zgYo7@?zN%kHvi=pZ@f|Z{BsJq-x@pwj1IyICwTpJ@6fBg?$^${Z};Qv`^CJw!gQyH
zd7&rHTp%#LNZld}qHbh0wS+fvP%~<JgT&k_*b6(RQY#wNg~4UBVb)Y?>RJNKuU8s0
z42JEN@1-Wj6Cn$<;%2R0r5<&LinWTV8Ps4rsBWoSO=NYwidSe(qa<rEk#-c=;y!c0
zjAuMYFgw+h=Im7xA>izMx(N|&>l+Pe8@qS@?8*~Qa2ycbf8;uZ$&O)K52=;)L^wj=
z`Wb=iMW_4M42J6n+pg$*cAB|E?+3U4?TzCN&W;H_j`#UFUh+=zJZl>q6Fppj=Q*C|
zU4wS7zzNp}k=-Y8K6uj}DLjs7Q4HT8b?A}2oaZ{UM1gvqqFpc29$)wxvio^Xx_%AO
zUJp#Lg8(@=j)s9KLe)2tr#^wB$G3-A$;0`ueBm;O`X8Sj<9(b*lsVZWP=D%R#zZeC
z@g7d}`z9IW^l`Gpb3R+aab?WM!yu6pBzfe@AaIa;-u`F%udp)I0>H!Xx<YA#5)2dl
zBMcI$5BmHbPVi5@jyymN$O72t$3}Mv4SnnwwxEdv9^>o>s19|*B!KTr0>dA(hYqx^
zEUiaiUsZ|oeqkH>*y8@xMfXoHVCQ`$ab2DIBP(<Fz^UJ-TTb=LocD-R{Q*vH8bb}D
ze#^L35Ir#l**yX$2CpEyAaFhxV_TvFBDFx#BTKa4qxzx3*nI*QxPBcn0{>(ZIeusl
zfWuvn+n7F4z&>V>Rgk@ySHRDCffwr)IUn)z<Vy(2^B)4m#|cdz2W)@fk)YXfF~Hc*
zj7gwv)5jyQlm*U@eLPu2;~q)a_p$4W(<}S1lYN(|aW6Q}CyN~K4^UUo`Nv;%asnR!
zn=MxAVcW~&0ly47zyc8^7ZdOU95NK2PdwS(vY+#{x%)i0yTy~dzna58e(ccUXUQSg
z=JVg!hF&@4e$(xK=UXkGe-)Wsz5d)O=I0RTcoOKI>m?B$D-4?!D{4E3L?0Z?5`M_n
z;o+UUhETwF5n275IC&8vfB!|=jx2ky7a$Hu%=c_8Ee3onY-E3b2^ta)4dl7rhnQd5
zc;sVP+JP+3A>n#Iq9t#C(lP1^Ir<ULEZh2#==v_MUtNLu9(az6e(%0EUAEU*b`1NR
zDC>mAf##ii>Z4a)8`^&NN#}>J{nPJ3ulp}14k11ltmg}m1dWfeV0ra%vbEkiJ@i?x
z`!?r(^KlIG$)dU<`^#SDJveFI1lbQM&I&RGfoDraqiVAwugi|4Nhjdva?&2rVn;UW
z8ZGi8mmvUJT$U&jN20Xo8*z?Aku<{7lH?kr1=(c>bm8Ig00Vwx8F@yoLE)V~iLma1
zkyU8*Ijs<Q$f%>}AYo4UX!!Q+fvoLUKYE6bVRU{g9HMhJT+~bJam^^yHVHESMGyU9
zuls%8{qZD5rkjASn0!Dnw*Zr2f=L-k7Rov@jVu&>aoTc@mM%H^?8DPP`7uSIM;uQ3
zBh&BRh3W-|6*(Q_@b2s9k;{P#JLZIO_;+dgxW!KEevcDl4nODgP|tW5Ds&C&_&gt^
zdjD^Lf`e0BPHm+3HtxLrz8fFb?oYkL%$e2&!J+IF)>o=pWj&gh2@)LsvUlh=J?@`-
z+_$9RuOYT8Hm~$Be+Sr%5o~TzG`8J(k)Xp)+xo2RG{6P8SiyX!{Q`l>`tbAy5C<Jj
zGz17Sjy`%|+Oj|cUOWut32uNYVgWJNv_yU*7_n()<}jCVTHn2kf9&*rZGa%wNd-*U
z-#<i*T&vCqAF(eDe(U=a?>+qtk5dr$udg1W)^~tfvSzG9B2R$(tas=qkfF)$cl-cc
zryT6BPAcjO+zloWXU-7V#_1lo>>)%s&Ry#TP4Mrt&znCm`bg60wC;~^TKC5c!CLO5
z0+Yk^^ZC)s-@8rU8ha6rB=?)whZ(xHJgm(mu-H77f6z1Z8Rh=LlkT^#fq|VoPmt8r
zz<=yv{sC6T6=LG+6iq{@Kxb{I;SH-{5DEju0_8LmD-;UKB`9_%15nOEaX>i(WeUng
zD0n6HIjq+%5R?$YnLqw@Zl|ec2Xa~gTJpo%cT%CNOBz#zkh^s2d=h%yw?l_`ox#_@
z>iR*_{wh6mr`P?jiu-?l2N3JzeuB(yh`HYPBIl`UZc{6%j1w{T%RL9z`^zXk45|=X
z^NQ6@A$N#&!jWvbz2hJYYbUm!)a~@+$4h%(dvM*Sp8<uBh8x6STE}LBPYpmmSbEK7
z8?tD~=Nfk1y<Z<X-1qsydVlVB_w+jCzTc_2`+=l__ca^356Q#>JDDHkVfG--lLr%n
zhkiOc<a1kxJ{95Xql<H%D#K?+wd(x9@yuuuK56c)=S;m`GOD9j*>68Hx(zg_jaF3n
z@;S<}qlQ}2fMC>h9a_~Id|!bkPwHkFs&FmDbPd;qXMYzOO@`})yVl}+l+6ZwfXc5Q
zr8V_huQke8-e}z@=FEIkg?g#nIOs65Tkts$t5(u#YF@3WF#MTO&4A(X6%)^0Sq@JG
zMxSj{=BO5<tq;tY$q`lBJHC-V7_MhIP^)F*DEWlgDer)MZ>8a*yi?dd_1??c|A^IH
zW_$0wmA(J{rBiNu&%Kq|_6eX<?6J;!EBV;XxKnzU0rysew%cc?^kbd(R`S8!1>g8O
zWp{KRlfI#wYR%`t6OAL$q^+YZoOEp81OBb6(-&yaHsT&Dv45@U6yDx*OlZ;QYWD&8
zi>yAp7j%j|+V>5Gl2fCisWr1gg1KJIR@6!Z$MSMR#eZ+Y3cw$nszuYlRKYXJPYR<D
zVn<t|+d9QbVNx7@7CG%oGP#hx+Pr=^?_8L|zd#|TD9R!f{Ci4KJW8;jgcYTrgbIWf
z3?Av<#l+cz{$OFQ*@h?KLi(eMva7&6coQb@CX?W~3MII^n)Yt5W)h0BphTeUkCycM
zS|sJki1Rzyxl}D{B#H~gU{-6yDk_YPZkdIs5!=j`@_MwmTZopto7waV9#hY!_p0%b
zQp`!o&783aG-bEd-pPfczUWL;YPI!dJ1l3GFprijT`p%!NnMMiZelrUsanjI!nL&}
zm>cm5*~o4+8j6+FbgH@*mg}o&LC52=Myi?(0Usj>dVy>~=Cw?a^hJ$ST}{vLtVLFe
zST>BU<>vH_{G7f^_=aLTtEIBODlInq(<y#6o!rbvX0c6xN2<Om%G+SOL2TDkE6F17
zi5kLD-4Ag(&?~CP^lT)xnG>6`*Gf9HlN$#%g<?x<={<clGvCDW-s?|%vH=)_{|@!q
z7IyNWOVfXAWzb<eBkucADK4jFQ3an8Uq!;O9>O;>Qqr3P48f<xeA-*am;ip*A0R{6
z)lzMkmt^>Ba%w9dBK@_sOmY)=@T&)Y+>_%WjP0S!#gbfKYmV>mZ*)7hlPxv<lY5Z*
zgyoslOl)I$Wo_;xtcc#n$2}-N>Z#=npKoNP`I{%{mrBiVB&FC+PD(sbf2Ksaf!BJw
z>@Mp+la*q4FVE#l^37a>td~|yns48uLbjxDWyR!v%n`DgptpTZX2sZd*3$EQ69+-h
zN5T--lA8zdVUDjx=i1^)C>F}6lg3(RvG7!Av5=Tic5{twf>9SePaON8)?>1ySF<TO
zu?BG{A1R!qXGBf!)iV5^4)K{+oBQcO;Tg=A@*63LWjS4rEw3a)C#}iF%$kuAQa9IN
zZ!N6|vx~(O{a(sO<jwrdYRj*11|0MIT4`@*HM1zrf1Oy<CV$09)-ytKC)<o=U1CpI
zTodF}PE0j2LX6Mq@=8|ZPuxq#^yv~C*Q!}D%+GIiJ#S8m*KnRD;cV1T+~>>ba3del
z>uToYeGX^Xq1?`Mu$(o%9*#>QtjW3gjW3SfwQ@GHcQeC(aSZ>ay0!9%##%beXQgQC
z?A|M{LavfCw#m5#=RVY9JNagu5n=t^RMT>uoa<Y&e0)o(CzfJxHbD+^aL%mhIb*(@
z6+MJUqUhO+Z$*n6%}fmvCq+r&^eR{gDauS0=U#Q3mPHGYb_G{)JBHgg@Pv>DkKe$L
znf?4tQT#WgsVUrCj1sOmkvmNFU=~i@W{=>gD2bamX~YAAWKwA6iDr8?1kzv<p^_?Y
zHuJyWJe+4dU|r4;@mTR)1r!I7%_I{BHu;5b?(>`J$`7oAq3wHqDIf7}q#|++_b3T}
zOTVb1-+(%?FF};TiEg`nGnhKtw$FHdJ~<o3`7h|Vir>v&VJ0!PGc^T`U@%EYIs7E5
zkfsvHuVb-N*~Rjww)X7_H|-%4+VH_x2D`<1C4lEQwp#YgHs=Qq{YN+{RXqRbdA6(M
zVA53T20V!UE5!Z||6&H=!?T?5o5k{;Q1E=rxMeRvqRn2i{*LD$Wd0nPzk6&xPWs#N
zBKDK{WKyVr$BW1GjgUT~I;oKbGTY1{F`<FS?|}*Ao&o;aRft}|e1Fou{>S}ApjatE
zKA#TXTwBB&WwE8-lTRWiTUIOIscW@~T)8|!E?jKuLd7<(TCThBx0)~ghyK%r&<*%s
Gvi}c^zcEVy

literal 0
HcmV?d00001

diff --git a/python-for-data-analysis/james_bond_data.xlsx b/python-for-data-analysis/james_bond_data.xlsx
new file mode 100644
index 0000000000000000000000000000000000000000..1e042705fc38619b41b62bd98b1c1a807c061cc0
GIT binary patch
literal 11269
zcmeIY1zQ|j);8QofW}>eLvRi5!QI`1ySqzp2m}opg1fuBy9Em#92$3d`<$8i&P>jH
zzu=kb?%G{_?R#BaweO{SDat@WV*+3RZ~y>+6kv3kX`v4R0K`E902lx`NF5P-I~P+s
z7XwvK2UBM~Mh{yXk{oDA>TCccc>e#6|HDt9EOAu6ml;*;R`N+?he3L^MhK4mBxn$w
zR!N|%FJYj>SSQQU@--{s5mop*mKA3;`sAuN>-o4vjh$^nQ20QrGGbKVP?wrM0Vh-c
z;4x(<4qm*IwiYNGlR$_C&%hwYEFJLGv9VW~O?2~vbQ!({7PdgZcINV+I@<a`Gh&H$
z5%<ta_lCUs8XDI~@hs~0G{&5jC5^ZK<u-#9bQGEQDz=+`z9Oln3XPF+v(rP0Oouad
z)BAZtW5_k;(71NwpA+jatsR_1a%}iD#gSJf+5>Ucbe%rBK3<*FpQEl6A6huDEDRWQ
zvV;OjgJu>1iq=te*yXHtlfHd|Sh=#JXFVi8A1OC6-uA5%n6zZY#+k_DlG)O4<PT<v
zDsXes2Kf~Z4L5OhDV!L;^|33MhTVY{yL-jFK|5%<>=H&D?joh|4LjKwI^gv_p8BN|
ze0rXI;LrL30|30fLID*2LoMson8~leT$2TB9RgS_4V+AEoS7K^IR8%_{}1cnzukIS
zyqrQWGh!%6@+oZScK&A^s<4dv2gz1aRlfkKRh0UeTnd7pom6j8Rq=zNB>da`o<>%F
z^2Hnuk=|^vl|`Xr@{%{Wmxrc2IJ&~pzH>?zcP!iNLvx$Ip1(<zkoKf@YmcQZZ7TXM
zGrUeNK6@@&jXKGwfe*yUe;bO;pBkt=Ag8rvbXNf}FRXG>9$MANnSGcrneP81x!?dv
zFq~WVcqSEV$l1tzslsQ-hV=R#Uroh=+p@|i%ZZ1~)4;^0>rynm6XV&3K|W(hnT!qn
zj&)LEkTUz)U%QU&d^FRuj}zEiI&?N16h&OL2KG>YSCU{9iLi9Ag1~`Q2nGCPJZzZU
z?VYTR?Cq`p@LPGRathnbsO^<?uiY2?6sHo><jQl(Q|j94So99Xs?DEQJfx1xPNvku
zUpuz*XcF}`!_ij~9JAKP+Qydd-%U<o{1B(cGj>8Z?4wkPh%3cif9|-DXJJhq`D7-2
zfotE~y%!8xpIDF<WK8rD1(3)^t5`=3-6F|&%8y6THbGA+A7p4VUypEx?6R@Y>~Ty!
zsiS`KlMm@*7tRw5`kpM)eWzK?x;L{xl4d>!>6;MQ!)C$#2&XH5ZLH-X`|FJmz398+
z2FQMD^Jx>xq=G2Kp0zl}Ws4>e4@rPXDK}78LgH7DrRm&E7NE``K_K!Qv;ZkA&Eng=
z4P!|{gG;JSt0wdOUWFR?Tg^>6Twq7ExR7>|I+^4e)pU!u9RnYiPGt1@j~TH#YQO1K
zHQHY4+yVV}Jr@)M{LJ%d#BEciEVN=UYwC;ku2q7Iqn;(*0m~@wN9*&F4X7<YSn(bj
zB&mh?exXHWY1#Cb`Of{sOF{|<D?UQj!mMJYqIyU_fHQqOA@r#hm{fa^oUgj4QvTv#
zHhyfzL#!gRCn8l_j%Icv{^d&Z<@LMNh_1Acq=;O-ey0MEc|j?+wRj$GA>mwM=$XMc
zNLr{p;b$yQplZU6E-T@e`%BBk(*!rpE3d-dtRDyN;`*IpE&8BCr@52sux%MuuRuc=
zToy5z^wY@WY~$6yNTTM7gM#xo5?Zkf>22;sy{z<gq!>{Do8#rB_6_SxT3GX(@!+@!
zZ4o#<YRqL0v({M{XFYCWQ6rTp3?Ni^tKV&Klp1_A(DM2t`Oq3m)Hy`1<M=*2<0KMn
z^b==d$pCP!1aDaSxUnJ?eSgZXB0l=d=T$tf__&hrar0<1o02c-s{`3i9CAKqV4D7&
z$AJQgDVJdWwt%^e4}gOJ^Y|b3{@>aBFWV0R4#mLQ@PGR#Q<jtI1FJT|OBl0zx*HbS
zk_!{rvDy&|+;APu$~)5cepl-Rv@Lp?3o=Yl_Mx7j@j<s+cH}K6jO%W?qDXXTFAN(H
z?;HE^%W)_;qmy!?Ac;2^=*Ndgr6&l;Y0enU0`WuiS(seAchr=4VYvllqF2o`p=?$Y
z%&x3f&QpXVVB0rZw-fO2N#(dasIIY*B#p-G*K4!L$_>o7AW!1yOFW<yACf0vdVh|T
z?yg(x2JWKm$xP03!n!;60rA({QW>HWc7C5w7m~0c31WYmc;{a^sjX_DO&8(E5t`1G
z3;NM3klD`g;QTsxrT<PDZjL|_M{oo`#0UW3f@l2G^f_CYnz}eM{W-AwVFNSbb?kdc
za6>^U$AYM*Nex5=F|I6H$*IRiO9w;;8Zz`#5Lq?HouJ$btF0KVS!MVu&rY1R;b(a@
z6Q~8L-1qqI<kCV22{P?t`-6|h=Asdox_fP`_^d6k5}?9H&V=%6It@sVAm|fTZ7+ku
zXl|vTtqN<aDJ~V<(xyR$R+EZ`uFG92wQ7pUP+7;~gTT0DYup0ryZ~781^7BaA$rwS
z<L8RRdTUE*-C&i~iUn5*Ts3kdQo4g%q(pSenR{h|Q5>v?wSHg5p^2@`jah5cv~vVX
z$`JMm%#J7%x1#%*m#;B+I1)4Yucge6-?SEo90I6RFFND5y1yi47`FTOgi2^GGNxCU
zW=(_kL5CZ>$Z{@L%gw|*nLFqTTuo%yk<k-dSKN3?9GPqo4~bQ-=Du6^TS&C1M2Zvz
z6g$oz$7ty@wiQ1~{-B4Gyqy;|cbp?eIt>jR`@DbYM|Zg>dfy-a7QUn6sdPyoP&b+A
z8peW|f@1s@Wdm9q1FLlyP~7?F0{(eQOk1%#;y@MiryTMoRB7<xJ_9N)E%c8lKwAa~
zWMWf&Sbp)fOlWBO@s;6gq2WSYycr6Uh}Z4;<KyGr=Jn;Z=j~-|Cy}3@ze_9%v46+Q
z-Px<J^Za)2y50T5%}Jv_GKkn7Bq-1+IAN~#eAnj9%lqne(@}T6(W}#$wbxo$x%YEc
z=gOiiOeMDcx@d0OkRSWdv5rXQ+M-;doG9~Jvsl8Of8mftGd9L6qij%}e}ETFMA6{1
zNmj}CLV9iI3Lbmtpxs`Wr)Uc96Tmw#{P_b(j~`}ucq1g*u{_DvDuQTu*kOFh5njiZ
zOZ~Q#aTPfUQ#X%q8ML1grU%Fu!Ka^;A}*II<a1z3vd43-kZ2B8xE*icR4oo1f0!5|
zAAV*KA^zv?ksTEE6sbE?rPcOZO!uNSxW3jC6^kuKhA%#Yn2cwR<w6!efuAzk+fXt5
z@U|zGs24fkQ}e;_X1$`9sjSDJxhie6-!hybP#BP-RyHVn2l~L%!RWV$!8AaAX~-1H
zlVU=JAexZ*_2Ye7MvyDJaStpnhJa>*<%g{f+Q`=1tgX)gb{gF+h8r3-$CPBr^jx7l
zTRPN;DWE9X6(s3iRZE{QdoNX1g&UtGqT4&4D)rQ2Gd)aCkZ;rzI&c9_wBh&-nJF@4
z>N!mr_dMK=DtVkrjF704=HQTXN%L}Z0}L-Yaalr1{6%_Bmp4df!<s^g9960g2W}V{
z@?1$GFkF-lHQtp*_d|_7i7<za(FXUD?uqQZ;hqUbnF=xbo$WvFkM8u{8z)YhxODu$
zRXO+_J7p601jy!e%%OhQ^x-?hN^aPg?ujngqboyTTY5^8>Dn{)Lp{y#r!*(}d^(ud
zC$fa1=#DA&La+Rcqk41rY}<47;KDsqH+JJw3B}1>oqG|p=;_Hht?%n&Pat?}Q_u@>
z4jg+<-drTvTsRp&fzl^@r95-;$U63%rVMI`r%vkb$#C>BZlw|0wM(=?3V7ik)M7Ko
zA==<sjHt`+HQ@4f$v)XNiCgH{9rN?YVlp;Pw++3iFH3W^L~81;#m^raY*!?htJ|vw
zmhh!emJ6h?mn&n}OKZ)0;TI75jL`(8UC!VJej#0GP!Vi_PsD0uWB_uO*(KGqsYN34
z!TltIij_W(DOVOPQ-KG1=bQBauZw9)<vX;d!gR9X#t<<^*H?{n)el?hgjUmN#EVjm
zl&vI!>)3NYfWLkM|59??oNA2eOm*1F)t5fVhc?IOK|szd{OPl90kVT>J!r|7XD!27
z0)C9Y*pM#dCT5N=$DT+4aCryu6&AHiJjQz5+N=<e?B)jFRfIOi%`!6bF$MdJ-RCQt
zfG^*?`;qOvgsgKz`FOdd+H|ez_E%+<mY2trX!OtchHf*LiuD6ib0If2osWm)PFqwH
z=Z6@}=|M%`7mG+2OTL%K;4d$i;Y7yZgWog_Ry$T^#Ia+MXaP#(Uu&%ru_hQ9I0;c!
z@C~!H0qNCW-0UVKr@vycF<V<0sxa-lSAV`Ke?KY?-A0XIRvQtyd(e9=URIV^F%$G7
zwH42B!L~~>9f~>r7A`t)7Lpu=$57u4o`bx1cC`CCI!YXR*TgkCz)JLz)j3BsX@1K5
zb|*C6TiejiDli7$a?i{pn<c(cZOl6p8CU5r@Z2nT@S_RI8+na@FKFZ9QB!gkPCTse
zOi|auxWg-|k)AQRO|07cYIS&c%iOmr9vrtSU8@QZ&cNHd(`ARqE_H7-T<)!UCp(Ko
zte;7%&`chUxr?i()D2EU<&2ehQ=A$Oh7}uKy4_g3jQB(bb6u146}x!)X3+r%9&CHa
zLM1gLkH-RXDl+;!0A~o;-F_(MQ31mR-!A$m%*%-)ShM0yM@@E*6E`T2Ocu!S7xeLF
z8NXMAyqs_KlFiz+XS}x@#cH)@Dr2Rs!G^6?7VBm}4Vz?#e((@2i_6$K+u}~^2W95)
z$?Fk^Z=aIGAwdu4a}7^hymqtM0qmHONOh73sCaxIbqt|Fo!5X=fRGuz7*?DNi70G3
zkV!zSDwVrE-;f6Pd5j0Wve@}B5o<Rov5{}zB4B)#vb>y!rXg62czg>g*6bW&Yzu0!
zjJ(;~dj0ft%{m&)tEbxZvYMW@_=^SIUl8dRBHB9a$~N;;668xdeE7}F5XM_afnUVI
zD^QfZqJkWahRbgBQGj1?Ojlu+$>8<PAMwPW?x==FQdZ$wj$V3lj81(>N{+5tjdkih
zr<yYLi0ov5v-AamO%h@fX8eVW^o4WxSoB<9;v89=RrXfh(-S(b#QKDICtoLZD;GI?
zeIN3l5`Qma928JCnSrx26@ovii+_eGE*7S?rc8gH|BO(MwZ`oTI8i%r_IXjg73i1Z
zjqtue$s})aI2tWVN4_oAvr0j8ZziGPZNVC@77EO<oR$e(^P*mckqpqEDRfNFkqc}S
z4%?B|)>gHlf_cCpv|+g2ewuU$ZSgw!Ffv7o7JpHOrOKoMDOwXJ!4{>{o#_Xf@e0W6
z(fWipDM|Mg6;F4?=e51mLxhro67I&_392zjwAjbkR4lYA`j=@|0^%A{vt)IU1X`si
zBr(L##PTwA+L$EFS$ZKn`M~3o&A3qLYxZG7XX&=l4Hgw;rcbhOEoS<bK2}W^m7qD1
z@yce4jA=uhMcgTU<5Pq%(xmm6hNs=dD6`Sm>n7-bSCD+naB`HYP+hr*8l#S+fQDiw
zTiULDIdT)-0l{1!e&p7gY3C|F32?v-Do{^m9oM#RU(TAL4?O-Mwwx*5uIzkH`CyH}
z%DHml)~+>V6oDW2tgX{ksexZ#t_Eu_gl%BZ^<!BlQ@*#GAg-Si`>dUATztHrK(WVy
zLtDr??8fWOHJ-`P(r26w<g;sOh;O+h_-51jT8N$n$^F`qAm?eQ02tOXi_kd=Dv`Is
znC=cdsF>C;9>E(k1g)4OA(Z0?!-`Y7^+71kh<Gf8w}<z)m05yf;19Ro-SOR~!eA^B
zq2SZ>j1$M{20f#_&;5zHzuz;<!}b9u6S4p1;3(_M4`PA)Uwf0!LPOcjqD&n=7b~??
zOdStbw;&?#4IN07kuw3g2+_tNwB<dTeKW*uX?d6}AKnLG!31&!z!v48Li+7SInYc%
zH@#_~l`h-kF5t)DEuj_)I*a;T@4a|DPnX_=Rysl@gq?*xCBp5X*0DL`fa$8hK$yT9
zVFq`_$!F)HwApMIn{}yh@?E0d)E<`MaN!3+VzjO4Q=<IOdhV9gO*<kXr%H1JbJp<!
zgj|7a>vbY3XQO?E@0*sZ$4~X<cE<{@Ik;WE#G!um`~<?-{d&$rM3?a(dE+=T0@E3x
zwuNzFNY=wzL5JnR^Da8qPBic8q?tizJ$}~Sut-C{5mX~}NEVVqPCTCe^^(;oJ(dS3
z?_4>?CNr{#vI8fKnaf|{bEbD{7VZZlxM5S=3R2!`db|>L2pjk;c?p=dAIK?MmVcJB
zylF8SqgLH^@AvTHvF)DTk%`E}p!C2yHPG~EJm*>=M?H#yoosD+tT=^vy>DryPnp!V
z-Ft(bw&Q7F)3W1YnZTD9O;`jZ=gdDypnQw1gn}&xWna*=G?hqoR!@D3%!s{s{2{0`
zwn!QoJwqf`kDc6r9$}_hlskoaCDru3PdrB5IG5D-agKzKdXtC^M3QB0o+c?jMrt>s
zqf;@B-}}qsm0LoZn>M)pI{B(rt|~LWTcXaMld8N|#G!)c(^P~{KT!tMg9}=FQ??p_
zrZ<XQ3pAscacgwGoMTA44r!5m$3+$rTelV^P=Ze-XKacuPDFgb4Z<W&YGP+!YTR(c
zrb=3xPp(S$0@=2)5!&tP&v<&15o)Q+%O`)&Ri7%WT!6ydYQsYOSQb)giL9T}a^6cH
z+WK7)NN`j5t`_*CnKS*Rs;oyYr2a9eN1kvfM0G{;9S7T3DH*h;S*Qc~s}<pxmlFJ<
zq(2nR!U8Go3kOZt=L+j#2T5TyH#f`vRV7>@CFy%jG{-nm35%`)BjVsk*P<W+v?K@K
zkKihCKq;H8?d1r=gxE|HQx)Pwg>f=f6LlkxSYfKo=DS#P)~{4_<!C4_mm_wGyq&b~
zelbZVIpMxes!s0#b#cnXmZ3;jci^L4IvOAuReQd}{{kX;LoznYo&;C~9%*_YeRy*_
zyxU0<_Ru-bEz_IFF6(RcZ9r0yD^`^ZZYj9NBnO0PG{1FRL!tFyNK{oyH&v$^b|<c?
zqaqN=w*i(qP?2*!j~WWbo%LmPk1QCb+Ro{vI5Spm_p$-Dg|~_!`KSMYex5q*Lw;`d
z0so_{0y`aSCHLZ_=iG8+efGK4^O%G!a*BZDYv5&UWZV)l)m7l~-lL)p+S7vJ3LUhP
z?=T0EB#xvG5$qJ#k{E$(TB5CH<mpY%3U$*LMxLK|217HP2QHJA$6C(2HO@}w*FX2}
zqxCcwt6iICufO8Q-<U)m-dOMq;SPQ^s2>sJJMZ>&xZ=<~k4=rgv3iBjJ?~EZ=uZ)_
z(>TGd!}$s>sr)^A4oL5TBZ2||u3!NGq<^?2XBST!Q|CX+hH5KzE6j+##8v*NSEnOx
z+w?#i961%JH!UB9cnvEf8K{I^SxoYsd5+g5?&F&*8WERd$du-$Nl~N*HDWOLQ&ZEd
zlQuSb2E&VWadd6bpH5gV&2Z<FOM>9bHG^);1~d)^Q5<b=gZORmYT-y!GdIfX=Y!&S
z)>);F5cF8yP~~&PYcHlD71Q-vD7DHc$4%W9iYiw)gjL1ecLqpWWw|A#SZgVb{?K)3
zwXbH5zu&UUt@~~bp_*<e>^ujpf{`<T7+bf%36jhr&^wyZ2QW^X4m;l@pJt2!$73Y}
ze2A1$(FA?4yp1PB(@=Y}niEh89gCC7l`7mv-f=<aFusYR%J(lCBMj_m*TDb5w4VxJ
z1^qS8u_A<HD99zQc_F9BBy$i6%g46KnXY)pXgyWL++zOpnIdeJm)wz$hr_bXO}}!@
z3#Ykr_GR871%V|p?|mMNq+O~KUPg}Jb5mtNP0-<SR%mX*8iB~|2izFOxSJ1#rE(BI
z9mX~drH#9#5vp-JmRkHv>F)Hbt-l-1G;O%#Vqq~pA@5wv?UPx2g<fI6e2TMgscli<
zbUfpKkXla`k=e|nn|iC6b#)TtDVQuk9rw;$n6JsOBPEQlxyDL5&y6+Vrb3c=3{3;N
z7hUuqMbEA!W^^96yqBmu)Vw>VfN$e9LKX0|M*ikzlOsos@}|N*L-eQJQu3gqKf|54
z)IxI}3!8MKn2zlog03rJaxZr<1hnzO#j2K2V#7^Z%_N|YPx`pDjtKpe?mER?6hV=Z
zsB`;vkJGihG(@e%XR`ZKxuZ~Hy7f)0sS-oVpTI{CF4;53=Ts~osy*1s$|tQAY_jgb
z>-M84!^1VhnD)x=UpI+Q5EafQSAG@VA95hHr*>v|CdgoWURpF?<P48H)sO7@?XN%K
z$Lzo2PMzSqDPj3aZv|nzdewbHD)818NMy_NP);l4J?2X!|9nJ!)_y#L(l(qp(YAEO
zdQn3Sr!hNx!7-A9cDq0J;WU9{UjX>or>;tuwR=8$K6`2ro~-+Z=|kKHpwp9XVdsCX
zz+-mRYITDH%2a#+0P~-UWbx6-)I`O_$<ogJPkqYJ0@<%{pgs#2zCwM(T!gWxrXEgI
zrC_|s9bR4<#^y!188);TFr)jzC`Ebs@{qY>cqGb#^-KyU98!IH`qLZ4I0$;7MY!rq
z+*Qs%JX7KllBNF@8Ff9pVdr=6%ptU_Se+Asd2CW;>~&`M^z1&UO#tm4B7kQTz0^U7
zeC^aLT@t&K4D`65R+B<{Dq0X}SBtK=3T08j?xjW?uFBIzoKjZr$w1736DUA`lIfqg
zrQ)ItKCj;0Hh$k>`X)Dx5M}(%LzDO<w(ufCC(K;AY`IhO8^c7gwk%WS^5m&m6dh%~
z-M4iawXzoCOtn(>_xppK)QBR_Dv!IAOe6iDBI=jwh%*Jsaop32`@;_UQ!h8m(W08^
z%N>eYbsdi6{C|mk$I)~2FM~!vosgP)(ZM-{(;K}xh*k=m$VZhuDKk&<Fsyr4W`|rm
zWYB|T&F({8#vq8ECXfw^%lm*E`?&|T{w4Wnh8jhDEyV#KwtpALGC)e(Ts7mWT~244
zR@bL~kVrpmo6lajpPG)8Hbh16QTA(2Cb5RB61vI9eGiEr`D_SIAek?`Xt@)jvIiBz
z!ZQ;+N%ZQmQ?IgGsPp3RY_<W5jYV8tYt@F5>HaWA8Zc%y)|&TSsu-Xm!g(K+2rLzp
zI%+Q%v8{kR*rW}>*GUY7=Grnx&W=imn%9A}2IFTH^?h+nUbamI#PM(UGd;Jur+MG`
z-+$=~OT^iRx_~|2IJ~OE*dQ)7ial$~3?T^g`v@QK6k%EW_#qchhc^2P?@U8NyaLw(
zR|MmM69WbNy?m;+I`&5%ASq7(YE3~i|Ca>rFA1W^!iuAEKgnnsu7YOKMOAZE`ls?$
z5#I*qqY^wEC!#dXCYx%60+e48Bdq(+sg_$vdHbOzI=>SY=M%}v1gZ#Q1k8lk%GpsW
z(xypEeiJL3z05+wi4E%e<^?Ap8kzx!JS#;?(T-<bXWr+i#!-V3oWt*hZYdF+Y|0hi
z_Z@!k8)81db%;GMTfQYW3ybZ$;5gR6>(cophEwx<vD#<^o7##iSG7EHx0f3#47vul
zeX@8*xUrQIWtSTD!;+PIp*t{malLgz#ID~Cgo6evbQ{W53x|9M4CJ7_B7(^fCtYE9
zm}%$aYy_>uPBbgUUyEJrqsoL|PLq1NS_{pUr*53w;KylQsrQ;7tSzE<y?==CJ3Pvm
zfr=)an9+XZPZzXebgl7T9XBvw7dC6|Q@MgQpB$1DRpNJAx(i@I{5g{Ot0?0VIe<u?
zl}ZnNC!<VUNvO@fzhWoGpdg?u;ZSJW5LpPvMdR#xK(lr(BW1?M?F``!A`B4*1heMt
z;w~buU>_gVM3tbjlG6NQ@7Puw&_n3Emfq24=~jIfc}V5h%0=_tesXj}kWPg6V$`<$
z?&CUKqRz(JD2syu!F;EqLnC5lcckc)TgagK>|>VLASp1O8s!37UACPQlEq~3728qc
z*_3R^wr*6Jmh#)QtF5i|?Se*6w;13()rUm%Z$n#N8RzY9c#&=szje}jHiuj+kFx17
zUVZ3g9m>8HRzJF#7+H!#13G16ZT0K3;7-pyV#CZHEnkQ(l?o90w6#BNA!fppRJ2Uh
zf!@JFl{s1Pz1<^nmG8>CTkkoA=`=yHn$*3<o_8WsbtbjO$_bet#Zh%o&vq8OU&a?=
zJH~$I;AOY%?@Jky;O5@IM*bO{LXipAWH_3_4@W_3J^1J?7E&xtK|C#sUDbI!YD^LK
zV=^E~xpMp+J)aXC={TRAnB6=K&k5o~=Pw0JBZRx!$=1OanToVIBY<z>!zb;^N7lt{
zj&<K4*N0XX`Ho^s)bf1GS_U0_>p8bm)5A%H1VEv{MP@#C6AMWw^-To3<E7TjxVZri
zM@>PBbwpPrduaa}Z<G7g$GE_9c#&@p1y%Wzn^AE?R9ka|ES4JXaIf0<;HHHC5<A7*
zv~`Gsoxw+NWQ7LatTM4TR&=s=aAq>LcQXBFyU_pksKCB3I$qB@m>Dw^1p9~*?;WG0
zzL1T5ql8<=tT{MvD(qxs`Yx0r{d%3r>WF@&pK<(g_nbS-q%^oJn2EW;O7*iOW-b8J
zUNnE?ZM)5nO?LP)W9h0ErMO&VdTp!}9K0WioG@9kx!q0hHXBkS$`#Ia?(!<p4C}!r
z92ZExdi9JcoL^=WHQ&E<OLs}VWvYT6gmy-}?NU?_brFRZAiXXuh7H)jwTjEm=%*mN
zD?I9weB28mO=UOz#dBiLb2zaS6uUVmuxLfwU`tSckiGc~^jqN*K*<eFI&|-cz)Ian
zBrvRC5fkh@MRpA}4||5RHv2gM^3n)wI*5cV2zs0l3iUV7;@po_L=D8r$$g>ml(Ppl
zSgTSv#)p3TM6os?lg4P_b-nibaO}s#MKqM#^%^0QMsMDSk&W9nNi22_j?4cZxC3Ds
zNTR^x!v<3m_20?&(ZS(=+yj&DpGQXgI5>wv{RDdRfD8#@`Beu8A8e#Z!Qf<}1f?E-
znXIiPO0B$M2i>Y*pe$_Dd{W%_jE5+QTx^HZPA4915?tBmr4|X<4ve{el;&G7s1%3@
z!u5e-^eF2?lUhBz1<i4ULXhj^k!g99hz|1E<WbCiM5&Xu{>EV&&hKEgtsmM@4+9GJ
zJejU-V;m)jfE8aibY{;$>_2Y8yZ4t%H)JK|pC2TJuvUYG(O4mJE#7HX`WDu$1(jh}
z*{Op86_Omq1RE?r{7aegkTC6s#r;?Q<nm=a2agowIR-9a%1Nl}fVke(pqRY*p>#B)
zFwMB<q^&mWeg%@TuSvM1+GiOKwKjGI%Se4nf?;>Ugk%ZvQp_lYPQ`i)H@W%>L8`j&
zwcUvE*eT)lreRmPKZSSvQ7cpWFnY&$w~txZeRkvRTby_fP(bzzom1P2Vcv#5qo+<q
zZiJ#X%BzJo3Q*T^Mp2CEtF9Zji*1%K`a3CpX`Rjb>t!P-re1yhvcs2Q3x5U75ReSu
z;P}5cT>fjp{x$xW_De;X{}k|_tzrKH{xPP2wc_6z#eN6=-Y)YOv<+OM{jGWCckqAq
zDEtKl06qc#1pohZEc`C#_l@hnBsC)Ze}Cd{+t|NL`Ms|EmlS<)8UntR->b~O3;4YP
z@RxvVa4G{9@K-(Hcj)gq&tFghqJKbt&wzfH@SiU9FFXLiLID8$&7uAd|4$?M@9>Iu
c{|5i3NmP`1172MK03Q4b0Q+ovnm?}o9|Ua)9RL6T

literal 0
HcmV?d00001

diff --git a/python-for-data-analysis/james_bond_data_cleansed.csv b/python-for-data-analysis/james_bond_data_cleansed.csv
new file mode 100644
index 0000000000..f67cf98f34
--- /dev/null
+++ b/python-for-data-analysis/james_bond_data_cleansed.csv
@@ -0,0 +1,26 @@
+Avg_User_IMDB,Avg_User_Rtn_Tom,Bond,Bond_Car_MFG,Budget ($ 000s),Film_Length,Kills_Bond,Martinis,Movie,Release,US_Gross,World_Gross,Budget,Release_Year
+7.3,7.7,Sean Connery,Sunbeam," $1,000.00 ",110,4,2,Dr. No,1962-06-01,16067035.0,59567035.0,1000.0,1962
+7.5,8.0,Sean Connery,Bently," $2,000.00 ",115,11,0,From Russia with Love,1963-08-01,24800000.0,78900000.0,2000.0,1963
+7.8,8.4,Sean Connery,Aston Martin," $3,000.00 ",110,9,1,Goldfinger,1964-05-01,51100000.0,124900000.0,3000.0,1964
+7.0,6.8,Sean Connery,Aston Martin," $9,000.00 ",130,20,0,Thunderball,1965-09-01,63600000.0,141200000.0,9000.0,1965
+6.9,6.3,Sean Connery,Toyota," $9,500.00 ",117,21,1,You Only Live Twice,1967-11-01,43100000.0,111600000.0,9500.0,1967
+6.8,6.7,George Lazenby,Mercury," $8,000.00 ",142,5,1,On Her Majesty's Secret Service,1969-07-01,22800000.0,82000000.0,8000.0,1969
+6.7,6.3,Sean Connery,Ford," $7,200.00 ",120,7,0,Diamonds Are Forever,1971-03-01,43800000.0,116000000.0,7200.0,1971
+6.8,5.9,Roger Moore,AMC," $7,000.00 ",121,8,0,Live and Let Die,1973-08-01,35400000.0,161800000.0,7000.0,1973
+6.7,5.1,Roger Moore,AMC," $7,000.00 ",125,1,0,The Man with the Golden Gun,1974-07-01,21000000.0,97600000.0,7000.0,1974
+7.1,6.8,Roger Moore,Lotus," $14,000.00 ",125,31,1,The Spy Who Loved Me,1977-04-01,46800000.0,185400000.0,14000.0,1977
+6.2,5.7,Roger Moore,Lotus," $31,000.00 ",126,12,1,Moonraker,1979-10-01,70300000.0,210300000.0,31000.0,1979
+6.8,6.3,Roger Moore,Citroen," $28,000.00 ",127,18,0,For Your Eyes Only,1981-06-01,54800000.0,195300000.0,28000.0,1981
+6.5,5.3,Roger Moore,Bajaj," $27,500.00 ",131,15,0,Octopussy,1983-03-01,67900000.0,187500000.0,27500.0,1983
+6.2,4.7,Roger Moore,Rolls Royce," $30,000.00 ",131,5,0,A View to a Kill,1985-10-01,50327960.0,152627960.0,30000.0,1985
+6.7,6.3,Timothy Dalton,Rolls Royce," $40,000.00 ",130,13,2,The Living Daylights,1987-05-01,51185000.0,191200000.0,40000.0,1987
+6.5,6.0,Timothy Dalton,Aston Martin," $42,000.00 ",133,10,1,License to Kill,1989-01-01,34667015.0,156167015.0,42000.0,1989
+7.2,6.9,Pierce Brosnan,BMW," $60,000.00 ",130,47,1,GoldenEye,1995-09-01,106429941.0,356429941.0,60000.0,1995
+6.4,6.0,Pierce Brosnan,Aston Martin," $110,000.00 ",119,30,1,Tomorrow Never Dies,1997-07-01,125304276.0,339504276.0,110000.0,1997
+6.3,5.7,Pierce Brosnan,BMW," $135,000.00 ",128,27,1,The World Is Not Enough,1999-06-01,126930660.0,361730660.0,135000.0,1999
+6.0,6.1,Pierce Brosnan,Aston Martin," $142,000.00 ",133,31,2,Die Another Day,2002-08-01,160942139.0,431942139.0,142000.0,2002
+7.9,7.8,Daniel Craig,Aston Martin," $102,000.00 ",144,11,3,Casino Royale,2006-02-01,167365000.0,596365000.0,102000.0,2006
+6.7,6.1,Daniel Craig,Aston Martin," $230,000.00 ",106,16,6,Quantum of Solace,2008-12-01,169368427.0,591692078.0,230000.0,2008
+7.8,8.2,Daniel Craig,Aston Martin," $200,000.00 ",143,26,1,Skyfall,2012-11-01,304360277.0,1108561108.0,200000.0,2012
+6.8,6.4,Daniel Craig,Aston Martin," $245,000.00 ",148,30,1,Spectre,2015-09-01,200074175.0,879620923.0,245000.0,2015
+7.3,7.3,Daniel Craig,Aston Martin," $275,000.00 ",163,14,1,No Time to Die,2021-11-01,160891007.0,759959662.0,275000.0,2021

From b0886f293bea45c9359752d60b0770a55d85cd33 Mon Sep 17 00:00:00 2001
From: gahjelle <geirarne@gmail.com>
Date: Mon, 20 Nov 2023 19:44:05 +0100
Subject: [PATCH 2/4] Rename notebook

---
 .../{Solution-New.ipynb => james_bond_analysis.ipynb}             | 0
 1 file changed, 0 insertions(+), 0 deletions(-)
 rename python-for-data-analysis/{Solution-New.ipynb => james_bond_analysis.ipynb} (100%)

diff --git a/python-for-data-analysis/Solution-New.ipynb b/python-for-data-analysis/james_bond_analysis.ipynb
similarity index 100%
rename from python-for-data-analysis/Solution-New.ipynb
rename to python-for-data-analysis/james_bond_analysis.ipynb

From 65af430d8fa4b9c861f220b4d480481d1f4daf10 Mon Sep 17 00:00:00 2001
From: gahjelle <geirarne@gmail.com>
Date: Mon, 20 Nov 2023 19:45:21 +0100
Subject: [PATCH 3/4] Reformat notebook

---
 python-for-data-analysis/README.md            |  2 +-
 .../james_bond_analysis.ipynb                 | 46 ++++++++++++-------
 2 files changed, 30 insertions(+), 18 deletions(-)

diff --git a/python-for-data-analysis/README.md b/python-for-data-analysis/README.md
index 8cb7b23c7f..9281b87392 100644
--- a/python-for-data-analysis/README.md
+++ b/python-for-data-analysis/README.md
@@ -6,7 +6,7 @@ The `james_bond_data.csv` file contains the original uncleansed data and is the
 
 A cleansed version of the original data is available in the `james_bond_data_cleansed.csv` file.
  
-The complete code is available in the `Solution-New.ipynb` Jupyter notebook.
+The complete code is available in the `james_bond_analysis.ipynb` Jupyter notebook.
 
 ## Setup
 
diff --git a/python-for-data-analysis/james_bond_analysis.ipynb b/python-for-data-analysis/james_bond_analysis.ipynb
index 6a361bcbc1..4a8ce4b46e 100644
--- a/python-for-data-analysis/james_bond_analysis.ipynb
+++ b/python-for-data-analysis/james_bond_analysis.ipynb
@@ -406,22 +406,32 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "data = james_bond_data.combine_first(\n",
-    "    pd.DataFrame({\"Avg_User_IMDB\": {10: 7.1}, \"Avg_User_Rtn_Tom\": {10: 6.8}})\n",
-    ").assign(\n",
-    "    US_Gross=lambda data: (\n",
-    "        data[\"US_Gross\"].replace(\"[$,]\", \"\", regex=True).astype(float)\n",
-    "    ),\n",
-    "    World_Gross=lambda data: (\n",
-    "        data[\"World_Gross\"].replace(\"[$,]\", \"\", regex=True).astype(float)\n",
-    "    ),\n",
-    "    Budget=lambda data: (\n",
-    "        data[\"Budget ($ 000s)\"].replace(\"[$,]\", \"\", regex=True).astype(float)\n",
-    "    ),\n",
-    "    Film_Length=lambda data: (data[\"Film_Length\"].str.rstrip(\"mins\").astype(int)),\n",
-    "    Release=lambda data: pd.to_datetime(data[\"Release\"], format=\"%B, %Y\"),\n",
-    "    Release_Year=lambda data: data[\"Release\"].dt.year\n",
-    ").drop_duplicates(ignore_index=True)\n",
+    "data = (\n",
+    "    james_bond_data.combine_first(\n",
+    "        pd.DataFrame(\n",
+    "            {\"Avg_User_IMDB\": {10: 7.1}, \"Avg_User_Rtn_Tom\": {10: 6.8}}\n",
+    "        )\n",
+    "    )\n",
+    "    .assign(\n",
+    "        US_Gross=lambda data: (\n",
+    "            data[\"US_Gross\"].replace(\"[$,]\", \"\", regex=True).astype(float)\n",
+    "        ),\n",
+    "        World_Gross=lambda data: (\n",
+    "            data[\"World_Gross\"].replace(\"[$,]\", \"\", regex=True).astype(float)\n",
+    "        ),\n",
+    "        Budget=lambda data: (\n",
+    "            data[\"Budget ($ 000s)\"]\n",
+    "            .replace(\"[$,]\", \"\", regex=True)\n",
+    "            .astype(float)\n",
+    "        ),\n",
+    "        Film_Length=lambda data: (\n",
+    "            data[\"Film_Length\"].str.rstrip(\"mins\").astype(int)\n",
+    "        ),\n",
+    "        Release=lambda data: pd.to_datetime(data[\"Release\"], format=\"%B, %Y\"),\n",
+    "        Release_Year=lambda data: data[\"Release\"].dt.year,\n",
+    "    )\n",
+    "    .drop_duplicates(ignore_index=True)\n",
+    ")\n",
     "\n",
     "duplicate_movies = [\"The Man with the Golden Gun\", \"The Living Daylights\"]\n",
     "data[data[\"Movie\"].isin(duplicate_movies)]"
@@ -721,7 +731,9 @@
    "source": [
     "length = data[\"Film_Length\"].value_counts(bins=7).sort_index()\n",
     "length.plot.bar(\n",
-    "    title=\"Film Length Distribution\", xlabel=\"Time Range (mins)\", ylabel=\"Count\"\n",
+    "    title=\"Film Length Distribution\",\n",
+    "    xlabel=\"Time Range (mins)\",\n",
+    "    ylabel=\"Count\",\n",
     ")"
    ]
   },

From 150da332f4a25e49dc88b0c5fb47dc6baab1664d Mon Sep 17 00:00:00 2001
From: eyrei123 <88923476+eyrei123@users.noreply.github.com>
Date: Sun, 3 Dec 2023 13:45:56 +0000
Subject: [PATCH 4/4] File versions after TR2

---
 README.md                    |   54 +-
 data analysis results.ipynb  |  222 +++++++
 data_analysis_findings.ipynb | 1093 ++++++++++++++++++++++++++++++++++
 james_bond_data.csv          |   28 +
 james_bond_data.json         |    1 +
 james_bond_data.parquet      |  Bin 0 -> 11050 bytes
 james_bond_data.xlsx         |  Bin 0 -> 11269 bytes
 james_bond_data_cleansed.csv |   26 +
 8 files changed, 1387 insertions(+), 37 deletions(-)
 create mode 100644 data analysis results.ipynb
 create mode 100644 data_analysis_findings.ipynb
 create mode 100644 james_bond_data.csv
 create mode 100644 james_bond_data.json
 create mode 100644 james_bond_data.parquet
 create mode 100644 james_bond_data.xlsx
 create mode 100644 james_bond_data_cleansed.csv

diff --git a/README.md b/README.md
index a4f169fe5c..b714e41539 100644
--- a/README.md
+++ b/README.md
@@ -1,37 +1,17 @@
-# Real Python Materials
-
-Bonus materials, exercises, and example projects for Real Python's [Python tutorials](https://realpython.com).
-
-Build Status:
-[![GitHub Actions](https://img.shields.io/github/actions/workflow/status/realpython/materials/linters.yml?branch=master)](https://github.com/realpython/materials/actions)
-
-## Got a Question?
-
-The best way to get support for Real Python courses, articles, and code in this repository is to join one of our [weekly Office Hours calls](https://realpython.com/office-hours/) or to ask your question in the [RP Community Chat](https://realpython.com/community/).
-
-Due to time constraints, we cannot provide 1:1 support via GitHub. See you on Slack or on the next Office Hours call 🙂
-
-## Adding Source Code & Sample Projects to This Repo (RP Contributors)
-
-### Running Code Style Checks
-
-We use [flake8](http://flake8.pycqa.org/en/latest/) and [black](https://black.readthedocs.io/) to ensure a consistent code style for all of our sample code in this repository.
-
-Run the following commands to validate your code against the linters:
-
-```sh
-$ flake8
-$ black --check .
-```
-
-### Running Python Code Formatter
-
-We're using a tool called [black](https://black.readthedocs.io/) on this repo to ensure consistent formatting. On CI it runs in "check" mode to ensure any new files added to the repo follow PEP 8. If you see linter warnings that say something like "would reformat some_file.py" it means that black disagrees with your formatting.
-
-**The easiest way to resolve these errors is to run Black locally on the code and then commit those changes, as explained below.**
-
-To automatically re-format your code to be consistent with our code style guidelines, run [black](https://black.readthedocs.io/) in the repository root folder:
-
-```sh
-$ black .
-```
+# Using Python for Data Analysis
+
+This folder contains completed notebooks and other files used in the Real Python tutorial on [Using Python for Data Analysis](https://realpython.com/using-python-for-data-analysis/). 
+
+None of the files are mandatory to complete the tutorial, however, you may find them of use for reference during the tutorial.
+
+## Available Files:
+
+`data analysis findings.ipynb` is a Jupyter Notebook containing all the code used in the tutorial.
+`data analysis results.ipynb` is a Jupyter Notebook containing the final version of the cleansing and analysis code.
+`james_bond_data.csv` contains the data to be cleansed and analyzed in its original form, in CSV format.
+`james_bond_data.json` contains the data to be cleansed and analyzed in its original form, in JSON format.
+`james_bond_data.parquet` contains the data to be cleansed and analyzed in its original form, in parquet format.
+`james_bond_data.xlsx` contains the data to be cleansed and analyzed in its original form, in Microsoft Excel format.
+`james_bond_data_cleansed.csv` contains the cleansed data in its final form.
+
+## Although the tutorial can be completed in a range of Python environments, the use of Jupyter Notebook within JupyterLab is highly recommended.
\ No newline at end of file
diff --git a/data analysis results.ipynb b/data analysis results.ipynb
new file mode 100644
index 0000000000..fed90709d0
--- /dev/null
+++ b/data analysis results.ipynb	
@@ -0,0 +1,222 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "ade4bd3f-543b-460b-980f-0b41aab2c8b6",
+   "metadata": {},
+   "source": [
+    "# Data Cleansing Code"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a360772e-7829-4c15-9af9-d4596efc7351",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!python -m pip install pandas"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c98c7640-1472-4869-9fdd-f070d665ae1d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "\n",
+    "james_bond_data = pd.read_csv(\"james_bond_data.csv\").convert_dtypes()\n",
+    "\n",
+    "data = (\n",
+    "    james_bond_data.rename(columns=new_column_names)\n",
+    "    .combine_first(\n",
+    "        pd.DataFrame(\n",
+    "            {\"imdb_rating\": {10: 7.1}, \"rotten_tomatoes_rating\": {10: 6.8}}\n",
+    "        )\n",
+    "    )\n",
+    "    .assign(\n",
+    "        gross_income_usa=lambda data: (\n",
+    "            data[\"gross_income_usa\"]\n",
+    "            .replace(\"[$,]\", \"\", regex=True)\n",
+    "            .astype(float)\n",
+    "        ),\n",
+    "        gross_income_world=lambda data: (\n",
+    "            data[\"gross_income_world\"]\n",
+    "            .replace(\"[$,]\", \"\", regex=True)\n",
+    "            .astype(float)\n",
+    "        ),\n",
+    "        movie_budget=lambda data: (\n",
+    "            data[\"movie_budget\"].replace(\"[$,]\", \"\", regex=True).astype(float)\n",
+    "            * 1000\n",
+    "        ),\n",
+    "        film_length=lambda data: (\n",
+    "            data[\"film_length\"]\n",
+    "            .str.removesuffix(\"mins\")\n",
+    "            .astype(int)\n",
+    "            .replace(1200, 120)\n",
+    "        ),\n",
+    "        release_date=lambda data: pd.to_datetime(\n",
+    "            data[\"release_date\"], format=\"%B, %Y\"\n",
+    "        ),\n",
+    "        release_Year=lambda data: data[\"release_date\"].dt.year,\n",
+    "        bond_actor=lambda data: (\n",
+    "            data[\"bond_actor\"]\n",
+    "            .str.replace(\"Shawn\", \"Sean\")\n",
+    "            .str.replace(\"MOORE\", \"Moore\")\n",
+    "        ),\n",
+    "        car_manufacturer=lambda data: data[\"car_manufacturer\"].str.replace(\n",
+    "            \"Astin\", \"Aston\"\n",
+    "        ),\n",
+    "        martinis_consumed=lambda data: data[\"martinis_consumed\"].replace(\n",
+    "            -6, 6\n",
+    "        ),\n",
+    "    )\n",
+    ").drop_duplicates(ignore_index=True)\n",
+    "\n",
+    "data.to_csv(\"james_bond_data_cleansed.csv\", index=False)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f50918ee-e61f-46b2-b0c2-1ffa2c62bbc0",
+   "metadata": {},
+   "source": [
+    "# Data Analysis Code"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "86817f68-05a0-4235-a1c8-a5d1f6e9141e",
+   "metadata": {},
+   "source": [
+    "## Performing a Regression Analysis"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "bee6d6cb-e418-4c1d-8b75-604b9ab2e63d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!python -m pip install matplotlib scikit-learn"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "669fb9d7-d744-4e6b-899e-a69aebec53ed",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.linear_model import LinearRegression\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "from sklearn.linear_model import LinearRegression\n",
+    "\n",
+    "x = data.loc[:, [\"imdb_rating\"]]\n",
+    "y = data.loc[:, \"rotten_tomatoes_rating\"]\n",
+    "\n",
+    "model = LinearRegression()\n",
+    "model.fit(x, y)\n",
+    "\n",
+    "r_squared = f\"R-Squared: {model.score(x, y):.2f}\"\n",
+    "best_fit = f\"y = {model.coef_[0]:.4f}x{model.intercept_:+.4f}\"\n",
+    "y_pred = model.predict(x)\n",
+    "\n",
+    "fig, ax = plt.subplots()\n",
+    "ax.scatter(x, y)\n",
+    "ax.plot(x, y_pred, color=\"red\")\n",
+    "ax.text(7.25, 5.5, r_squared, fontsize=10)\n",
+    "ax.text(7.25, 7, best_fit, fontsize=10)\n",
+    "ax.set_title(\"Scatter Plot of Ratings\")\n",
+    "ax.set_xlabel(\"Average IMDB Rating\")\n",
+    "ax.set_ylabel(\"Average Rotten Tomatoes Rating\")\n",
+    "# fig.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b38df412-c320-49fb-93ae-e253405537a8",
+   "metadata": {},
+   "source": [
+    "## Investigating a Statistical Distribution"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "938e5942-e57f-4e41-99f1-215cfb37d0df",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [],
+   "source": [
+    "# fig, ax = plt.subplots()\n",
+    "length = data[\"film_length\"].value_counts(bins=7).sort_index()\n",
+    "length.plot.bar(\n",
+    "    title=\"Film Length Distribution\",\n",
+    "    xlabel=\"Time Range (mins)\",\n",
+    "    ylabel=\"Count\",\n",
+    ")\n",
+    "# fig.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ff4e9955-baf4-48eb-b032-fbf55f439194",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data[\"film_length\"].agg([\"mean\", \"max\", \"min\", \"std\"])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1b14c433-c3a6-4484-bc0a-26825bd1e870",
+   "metadata": {},
+   "source": [
+    "## Finding No Relationship"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2bb83374-347f-4cf6-bc21-8180a003371d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "fig, ax = plt.subplots()\n",
+    "ax.scatter(data[\"imdb_rating\"], data[\"bond_kills\"])\n",
+    "ax.set_title(\"Scatter Plot of Kills vs Ratings\")\n",
+    "ax.set_xlabel(\"Average IMDb Rating\")\n",
+    "ax.set_ylabel(\"Kills by Bond\")\n",
+    "fig.show()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.0"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/data_analysis_findings.ipynb b/data_analysis_findings.ipynb
new file mode 100644
index 0000000000..e1a3e0f216
--- /dev/null
+++ b/data_analysis_findings.ipynb
@@ -0,0 +1,1093 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "ade4bd3f-543b-460b-980f-0b41aab2c8b6",
+   "metadata": {},
+   "source": [
+    "# Acquiring Your Data"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "83ad2114-5ed8-4a90-85fa-adea5eda4392",
+   "metadata": {},
+   "source": [
+    "## Reading Data From CSV Files"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a360772e-7829-4c15-9af9-d4596efc7351",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!python -m pip install pandas"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2e52f486-232e-440b-8585-90416e4300c2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "\n",
+    "james_bond_data = pd.read_csv(\"james_bond_data.csv\").convert_dtypes()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "797f69eb-3108-45d3-9a67-58c43593abf1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "james_bond_data.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e47c1f9b-b390-4035-956b-622615b57f32",
+   "metadata": {},
+   "source": [
+    "## Reading Data From Other Sources"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1d85aee9-cfeb-460b-9fe8-f3c7e7dfb764",
+   "metadata": {},
+   "source": [
+    "### Reading JSON"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7465cd11-dad4-4741-9372-f825b28c33d6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "\n",
+    "james_bond_data = pd.read_json(\"james_bond_data.json\").convert_dtypes()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "47a0e4a6-0ed9-4253-9833-0ad22c49b968",
+   "metadata": {},
+   "source": [
+    "### Reading Excel"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a0364b81-64a0-4098-89fc-e58bd6d68257",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "! python -m pip install openpyxl"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8302139f-52dc-4f95-aa9a-96040ae5d82b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import openpyxl\n",
+    "import pandas as pd\n",
+    "\n",
+    "james_bond_data = pd.read_excel(\"james_bond_data.xlsx\").convert_dtypes()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "be4a1143-c966-4056-8a5e-3bdebe2a9b1f",
+   "metadata": {},
+   "source": [
+    "### Reading Parquet"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f36ef600-e6ba-4cc6-9ee3-0cbf369a4be2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!python -m pip install pyarrow"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c86284a2-9073-4240-b4d5-5e8b0373fc27",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "\n",
+    "james_bond_data = pd.read_parquet(\n",
+    "    \"james_bond_data.parquet\"\n",
+    ").convert_dtypes()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "69f884c2-92e8-4db3-bd63-84007f654808",
+   "metadata": {},
+   "source": [
+    "### Scraping HTML"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b902722d-9648-4124-80b0-64004342170d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!python -m pip install lxml"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1fb2ff9c-3030-4f4a-be30-c2ab68452a21",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "\n",
+    "james_bond_data_html = pd.read_html(\n",
+    "    \"https://en.wikipedia.org/wiki/List_of_James_Bond_novels_and_short_stories\"\n",
+    ")\n",
+    "james_bond_data = james_bond_data_html[1].convert_dtypes()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "31068de2-9864-434a-9652-b115d1131684",
+   "metadata": {},
+   "source": [
+    "# Cleansing Your Data With Python"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e0dcca3b-6e71-481d-a071-6218012db962",
+   "metadata": {},
+   "source": [
+    "## Creating Meaningful Column Names"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d70997b9-3c75-4165-b034-8544bd084c04",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "new_column_names = {\n",
+    "    \"Release\": \"release_date\",\n",
+    "    \"Movie\": \"movie_title\",\n",
+    "    \"Bond\": \"bond_actor\",\n",
+    "    \"Bond_Car_MFG\": \"car_manufacturer\",\n",
+    "    \"US_Gross\": \"gross_income_usa\",\n",
+    "    \"World_Gross\": \"gross_income_world\",\n",
+    "    \"Budget ($ 000s)\": \"movie_budget\",\n",
+    "    \"Film_Length\": \"film_length\",\n",
+    "    \"Avg_User_IMDB\": \"imdb_rating\",\n",
+    "    \"Avg_User_Rtn_Tom\": \"rotten_tomatoes_rating\",\n",
+    "    \"Martinis\": \"martinis_consumed\",\n",
+    "    \"Kills_Bond\": \"bond_kills\",\n",
+    "}\n",
+    "\n",
+    "data = james_bond_data.rename(columns=new_column_names)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "937b9121-b7ae-4f7e-800d-bfcc2689c98a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data.columns"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e432b28e-257b-422b-b2f8-06f41608391b",
+   "metadata": {},
+   "source": [
+    "## Dealing With Missing Data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d497e64c-aa7e-4d09-8de1-f529939d58f9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b29d5a34-c930-4ce2-898c-b9e8aa7f771d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data.loc[data.isna().any(axis=\"columns\")]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1db9201a-11c1-4cdd-9625-d70cee736191",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = james_bond_data.rename(columns=new_column_names).combine_first(\n",
+    "    pd.DataFrame(\n",
+    "        {\"imdb_rating\": {10: 7.1}, \"rotten_tomatoes_rating\": {10: 6.8}}\n",
+    "    )\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "49d06d77-49b0-4e89-b228-8583650595af",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pd.DataFrame({\"imdb_rating\": {10: 7.1}, \"rotten_tomatoes_rating\": {10: 6.8}})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f4af51fb-fd1f-4570-b16f-6f20e0b65473",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data.loc[data.isna().any(axis=\"columns\")]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f6297c81-4c63-4eff-95e3-4a944bb5fe03",
+   "metadata": {},
+   "source": [
+    "## Correcting Invalid Data Types"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "916c91b8-7888-40fc-bce7-247837508adf",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data[\n",
+    "    [\"gross_income_usa\", \"gross_income_world\", \"movie_budget\", \"film_length\"]\n",
+    "].head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "001996e3-2fce-4228-a873-b78eef613bba",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data[\n",
+    "    [\"gross_income_usa\", \"gross_income_world\", \"movie_budget\", \"film_length\"]\n",
+    "].head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "880e4710-1c11-4de2-a2c3-97a9672ce6f7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = (\n",
+    "    james_bond_data.rename(columns=new_column_names)\n",
+    "    .combine_first(\n",
+    "        pd.DataFrame(\n",
+    "            {\"imdb_rating\": {10: 7.1}, \"rotten_tomatoes_rating\": {10: 6.8}}\n",
+    "        )\n",
+    "    )\n",
+    "    .assign(\n",
+    "        gross_income_usa=lambda data: (\n",
+    "            data[\"gross_income_usa\"]\n",
+    "            .replace(\"[$,]\", \"\", regex=True)\n",
+    "            .astype(float)\n",
+    "        ),\n",
+    "    )\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ae9c1d1b-a620-43c5-a199-eb6a7bff7ce2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = (\n",
+    "    james_bond_data.rename(columns=new_column_names)\n",
+    "    .combine_first(\n",
+    "        pd.DataFrame(\n",
+    "            {\"imdb_rating\": {10: 7.1}, \"rotten_tomatoes_rating\": {10: 6.8}}\n",
+    "        )\n",
+    "    )\n",
+    "    .assign(\n",
+    "        gross_income_usa=lambda data: (\n",
+    "            data[\"gross_income_usa\"]\n",
+    "            .replace(\"[$,]\", \"\", regex=True)\n",
+    "            .astype(float)\n",
+    "        ),\n",
+    "        gross_income_world=lambda data: (\n",
+    "            data[\"gross_income_world\"]\n",
+    "            .replace(\"[$,]\", \"\", regex=True)\n",
+    "            .astype(float)\n",
+    "        ),\n",
+    "        movie_budget=lambda data: (\n",
+    "            data[\"movie_budget\"].replace(\"[$,]\", \"\", regex=True).astype(float)\n",
+    "        ),\n",
+    "    )\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8331b98e-169f-4d3b-9b88-0ece7ddc8dea",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = (\n",
+    "    james_bond_data.rename(columns=new_column_names)\n",
+    "    .combine_first(\n",
+    "        pd.DataFrame(\n",
+    "            {\"imdb_rating\": {10: 7.1}, \"rotten_tomatoes_rating\": {10: 6.8}}\n",
+    "        )\n",
+    "    )\n",
+    "    .assign(\n",
+    "        gross_income_usa=lambda data: (\n",
+    "            data[\"gross_income_usa\"]\n",
+    "            .replace(\"[$,]\", \"\", regex=True)\n",
+    "            .astype(float)\n",
+    "        ),\n",
+    "        gross_income_world=lambda data: (\n",
+    "            data[\"gross_income_world\"]\n",
+    "            .replace(\"[$,]\", \"\", regex=True)\n",
+    "            .astype(float)\n",
+    "        ),\n",
+    "        movie_budget=lambda data: (\n",
+    "            data[\"movie_budget\"].replace(\"[$,]\", \"\", regex=True).astype(float)\n",
+    "        ),\n",
+    "        film_length=lambda data: (\n",
+    "            data[\"film_length\"].str.removesuffix(\"mins\").astype(int)\n",
+    "        ),\n",
+    "    )\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f6340b1f-3b1c-42e6-9b69-e981f645d77b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data[\n",
+    "    [\"gross_income_usa\", \"gross_income_world\", \"movie_budget\", \"film_length\"]\n",
+    "].info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7025fbd2-ce44-4efe-88c9-9f51830776c2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data[\n",
+    "    [\"gross_income_usa\", \"gross_income_world\", \"movie_budget\", \"film_length\"]\n",
+    "].head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d45b9b42-7c71-422f-9ddb-ea659e5385c9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data[[\"release_date\"]].info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0f5dacf7-2f6c-47f4-b875-7d36f2251627",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data[[\"release_date\"]].head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ed0ead0e-7310-4c82-86d5-2480a95f1525",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = (\n",
+    "    james_bond_data.rename(columns=new_column_names)\n",
+    "    .combine_first(\n",
+    "        pd.DataFrame(\n",
+    "            {\"imdb_rating\": {10: 7.1}, \"rotten_tomatoes_rating\": {10: 6.8}}\n",
+    "        )\n",
+    "    )\n",
+    "    .assign(\n",
+    "        gross_income_usa=lambda data: (\n",
+    "            data[\"gross_income_usa\"]\n",
+    "            .replace(\"[$,]\", \"\", regex=True)\n",
+    "            .astype(float)\n",
+    "        ),\n",
+    "        gross_income_world=lambda data: (\n",
+    "            data[\"gross_income_world\"]\n",
+    "            .replace(\"[$,]\", \"\", regex=True)\n",
+    "            .astype(float)\n",
+    "        ),\n",
+    "        movie_budget=lambda data: (\n",
+    "            data[\"movie_budget\"].replace(\"[$,]\", \"\", regex=True).astype(float)\n",
+    "        ),\n",
+    "        film_length=lambda data: (\n",
+    "            data[\"film_length\"].str.removesuffix(\"mins\").astype(int)\n",
+    "        ),\n",
+    "        release_date=lambda data: pd.to_datetime(\n",
+    "            data[\"release_date\"], format=\"%B, %Y\"\n",
+    "        ),\n",
+    "        release_year=lambda data: data[\"release_date\"].dt.year,\n",
+    "    )\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9f147876-7348-43e9-ac6a-3f3df6ee2af9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data[[\"release_date\", \"release_year\"]].head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "47d4868a-94d8-4d36-85b9-b0c9a6203a8a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data[[\"release_date\", \"release_year\"]].info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b2c7922a-916e-4e01-829b-77cbb2205153",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data.info()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "89653d81-3bcd-4078-83cb-ad4b2fa560e6",
+   "metadata": {},
+   "source": [
+    "## Fixing Inconsistencies in Data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "47a41ef3-751a-41ed-869d-9f2c45509196",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data[[\"gross_income_usa\", \"gross_income_world\", \"movie_budget\"]].head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "bc483320-7895-4368-a672-b98f8d0c9755",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = (\n",
+    "    james_bond_data.rename(columns=new_column_names)\n",
+    "    .combine_first(\n",
+    "        pd.DataFrame(\n",
+    "            {\"imdb_rating\": {10: 7.1}, \"rotten_tomatoes_rating\": {10: 6.8}}\n",
+    "        )\n",
+    "    )\n",
+    "    .assign(\n",
+    "        gross_income_usa=lambda data: (\n",
+    "            data[\"gross_income_usa\"]\n",
+    "            .replace(\"[$,]\", \"\", regex=True)\n",
+    "            .astype(float)\n",
+    "        ),\n",
+    "        gross_income_world=lambda data: (\n",
+    "            data[\"gross_income_world\"]\n",
+    "            .replace(\"[$,]\", \"\", regex=True)\n",
+    "            .astype(float)\n",
+    "        ),\n",
+    "        movie_budget=lambda data: (\n",
+    "            data[\"movie_budget\"].replace(\"[$,]\", \"\", regex=True).astype(float)\n",
+    "            * 1000\n",
+    "        ),\n",
+    "        film_length=lambda data: (\n",
+    "            data[\"film_length\"].str.removesuffix(\"mins\").astype(int)\n",
+    "        ),\n",
+    "        release_date=lambda data: pd.to_datetime(\n",
+    "            data[\"release_date\"], format=\"%B, %Y\"\n",
+    "        ),\n",
+    "        release_Year=lambda data: data[\"release_date\"].dt.year,\n",
+    "    )\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c6cbd7ea-e168-442e-8dd9-e2955288fa57",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data[[\"gross_income_usa\", \"gross_income_world\", \"movie_budget\"]].head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8bdaa8b1-9f2e-46a5-b53a-c1ae4c201c99",
+   "metadata": {},
+   "source": [
+    "## Correcting Spelling Errors"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e442e51a-28fd-42d7-94b0-aaf1abe5d9a8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data[\"bond_actor\"].value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f9863aa7-b5db-4ab1-be63-727ff437b63b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = (\n",
+    "    james_bond_data.rename(columns=new_column_names)\n",
+    "    .combine_first(\n",
+    "        pd.DataFrame(\n",
+    "            {\"imdb_rating\": {10: 7.1}, \"rotten_tomatoes_rating\": {10: 6.8}}\n",
+    "        )\n",
+    "    )\n",
+    "    .assign(\n",
+    "        gross_income_usa=lambda data: (\n",
+    "            data[\"gross_income_usa\"]\n",
+    "            .replace(\"[$,]\", \"\", regex=True)\n",
+    "            .astype(float)\n",
+    "        ),\n",
+    "        gross_income_world=lambda data: (\n",
+    "            data[\"gross_income_world\"]\n",
+    "            .replace(\"[$,]\", \"\", regex=True)\n",
+    "            .astype(float)\n",
+    "        ),\n",
+    "        movie_budget=lambda data: (\n",
+    "            data[\"movie_budget\"].replace(\"[$,]\", \"\", regex=True).astype(float)\n",
+    "            * 1000\n",
+    "        ),\n",
+    "        film_length=lambda data: (\n",
+    "            data[\"film_length\"].str.removesuffix(\"mins\").astype(int)\n",
+    "        ),\n",
+    "        release_date=lambda data: pd.to_datetime(\n",
+    "            data[\"release_date\"], format=\"%B, %Y\"\n",
+    "        ),\n",
+    "        release_Year=lambda data: data[\"release_date\"].dt.year,\n",
+    "        bond_actor=lambda data: (\n",
+    "            data[\"bond_actor\"]\n",
+    "            .str.replace(\"Shawn\", \"Sean\")\n",
+    "            .str.replace(\"MOORE\", \"Moore\")\n",
+    "        ),\n",
+    "    )\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e313152b-92b4-43a8-8483-637281a1f04d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data[\"bond_actor\"].value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a26b138d-72e5-4e15-a875-ee65023545d1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data[\"car_manufacturer\"].value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fd4ae142-e339-4601-b0a4-84375eb28c02",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = (\n",
+    "    james_bond_data.rename(columns=new_column_names)\n",
+    "    .combine_first(\n",
+    "        pd.DataFrame(\n",
+    "            {\"imdb_rating\": {10: 7.1}, \"rotten_tomatoes_rating\": {10: 6.8}}\n",
+    "        )\n",
+    "    )\n",
+    "    .assign(\n",
+    "        gross_income_usa=lambda data: (\n",
+    "            data[\"gross_income_usa\"]\n",
+    "            .replace(\"[$,]\", \"\", regex=True)\n",
+    "            .astype(float)\n",
+    "        ),\n",
+    "        gross_income_world=lambda data: (\n",
+    "            data[\"gross_income_world\"]\n",
+    "            .replace(\"[$,]\", \"\", regex=True)\n",
+    "            .astype(float)\n",
+    "        ),\n",
+    "        movie_budget=lambda data: (\n",
+    "            data[\"movie_budget\"].replace(\"[$,]\", \"\", regex=True).astype(float)\n",
+    "            * 1000\n",
+    "        ),\n",
+    "        film_length=lambda data: (\n",
+    "            data[\"film_length\"].str.removesuffix(\"mins\").astype(int)\n",
+    "        ),\n",
+    "        release_date=lambda data: pd.to_datetime(\n",
+    "            data[\"release_date\"], format=\"%B, %Y\"\n",
+    "        ),\n",
+    "        release_Year=lambda data: data[\"release_date\"].dt.year,\n",
+    "        bond_actor=lambda data: (\n",
+    "            data[\"bond_actor\"]\n",
+    "            .str.replace(\"Shawn\", \"Sean\")\n",
+    "            .str.replace(\"MOORE\", \"Moore\")\n",
+    "        ),\n",
+    "        car_manufacturer=lambda data: data[\"car_manufacturer\"].str.replace(\n",
+    "            \"Astin\", \"Aston\"\n",
+    "        ),\n",
+    "    )\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c596022b-02a4-40c0-ac5f-d0b0643a7a4a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data[\"car_manufacturer\"].value_counts()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "50c80bc8-fdb9-4c28-af5a-cd6b66c7a01d",
+   "metadata": {},
+   "source": [
+    "## Checking For Invalid Outliers"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8260f6b1-6d7f-4338-95b7-8946d69a92e2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data[[\"film_length\", \"martinis_consumed\"]].describe()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c73fe06b-5f42-4357-9b0f-2e460bf0dacf",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = (\n",
+    "    james_bond_data.rename(columns=new_column_names)\n",
+    "    .combine_first(\n",
+    "        pd.DataFrame(\n",
+    "            {\"imdb_rating\": {10: 7.1}, \"rotten_tomatoes_rating\": {10: 6.8}}\n",
+    "        )\n",
+    "    )\n",
+    "    .assign(\n",
+    "        gross_income_usa=lambda data: (\n",
+    "            data[\"gross_income_usa\"]\n",
+    "            .replace(\"[$,]\", \"\", regex=True)\n",
+    "            .astype(float)\n",
+    "        ),\n",
+    "        gross_income_world=lambda data: (\n",
+    "            data[\"gross_income_world\"]\n",
+    "            .replace(\"[$,]\", \"\", regex=True)\n",
+    "            .astype(float)\n",
+    "        ),\n",
+    "        movie_budget=lambda data: (\n",
+    "            data[\"movie_budget\"].replace(\"[$,]\", \"\", regex=True).astype(float)\n",
+    "            * 1000\n",
+    "        ),\n",
+    "        film_length=lambda data: (\n",
+    "            data[\"film_length\"]\n",
+    "            .str.removesuffix(\"mins\")\n",
+    "            .astype(int)\n",
+    "            .replace(1200, 120)\n",
+    "        ),\n",
+    "        release_date=lambda data: pd.to_datetime(\n",
+    "            data[\"release_date\"], format=\"%B, %Y\"\n",
+    "        ),\n",
+    "        release_Year=lambda data: data[\"release_date\"].dt.year,\n",
+    "        bond_actor=lambda data: (\n",
+    "            data[\"bond_actor\"]\n",
+    "            .str.replace(\"Shawn\", \"Sean\")\n",
+    "            .str.replace(\"MOORE\", \"Moore\")\n",
+    "        ),\n",
+    "        car_manufacturer=lambda data: data[\"car_manufacturer\"].str.replace(\n",
+    "            \"Astin\", \"Aston\"\n",
+    "        ),\n",
+    "        martinis_consumed=lambda data: data[\"martinis_consumed\"].replace(\n",
+    "            -6, 6\n",
+    "        ),\n",
+    "    )\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2abb5b80-48be-4a00-9483-4732b9a5d802",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data[[\"film_length\", \"martinis_consumed\"]].describe()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3e129b32-5e66-41cb-b938-8fd58bb94116",
+   "metadata": {},
+   "source": [
+    "## Removing Duplicate Data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "be7aad8b-ef3f-48a6-a9a0-de909133921f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data.loc[data.duplicated(keep=False)]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c98c7640-1472-4869-9fdd-f070d665ae1d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = (\n",
+    "    james_bond_data.rename(columns=new_column_names)\n",
+    "    .combine_first(\n",
+    "        pd.DataFrame(\n",
+    "            {\"imdb_rating\": {10: 7.1}, \"rotten_tomatoes_rating\": {10: 6.8}}\n",
+    "        )\n",
+    "    )\n",
+    "    .assign(\n",
+    "        gross_income_usa=lambda data: (\n",
+    "            data[\"gross_income_usa\"]\n",
+    "            .replace(\"[$,]\", \"\", regex=True)\n",
+    "            .astype(float)\n",
+    "        ),\n",
+    "        gross_income_world=lambda data: (\n",
+    "            data[\"gross_income_world\"]\n",
+    "            .replace(\"[$,]\", \"\", regex=True)\n",
+    "            .astype(float)\n",
+    "        ),\n",
+    "        movie_budget=lambda data: (\n",
+    "            data[\"movie_budget\"].replace(\"[$,]\", \"\", regex=True).astype(float)\n",
+    "            * 1000\n",
+    "        ),\n",
+    "        film_length=lambda data: (\n",
+    "            data[\"film_length\"]\n",
+    "            .str.removesuffix(\"mins\")\n",
+    "            .astype(int)\n",
+    "            .replace(1200, 120)\n",
+    "        ),\n",
+    "        release_date=lambda data: pd.to_datetime(\n",
+    "            data[\"release_date\"], format=\"%B, %Y\"\n",
+    "        ),\n",
+    "        release_Year=lambda data: data[\"release_date\"].dt.year,\n",
+    "        bond_actor=lambda data: (\n",
+    "            data[\"bond_actor\"]\n",
+    "            .str.replace(\"Shawn\", \"Sean\")\n",
+    "            .str.replace(\"MOORE\", \"Moore\")\n",
+    "        ),\n",
+    "        car_manufacturer=lambda data: data[\"car_manufacturer\"].str.replace(\n",
+    "            \"Astin\", \"Aston\"\n",
+    "        ),\n",
+    "        martinis_consumed=lambda data: data[\"martinis_consumed\"].replace(\n",
+    "            -6, 6\n",
+    "        ),\n",
+    "    )\n",
+    ").drop_duplicates(ignore_index=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ff05e0ae-4f9b-47a7-87f1-fb7630fabddc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data.loc[data.duplicated(keep=False)]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e1216a25-4791-4601-83ba-62513e4cc880",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data[\"movie_title\"].value_counts().head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2ba17e3f-3ce1-4885-a104-f60d254d9feb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    " data[\"bond_actor\"].value_counts()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "52db1351-36ed-4104-a999-345ebbc62214",
+   "metadata": {},
+   "source": [
+    "## Storing Your Cleansed Data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "575a774e-6913-41fb-8ff9-4d786f478007",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data.to_csv(\"james_bond_data_cleansed.csv\", index=False)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f50918ee-e61f-46b2-b0c2-1ffa2c62bbc0",
+   "metadata": {},
+   "source": [
+    "# Using Python for Data Analysis"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "86817f68-05a0-4235-a1c8-a5d1f6e9141e",
+   "metadata": {},
+   "source": [
+    "## Performing a Regression Analysis"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "bee6d6cb-e418-4c1d-8b75-604b9ab2e63d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!python -m pip install matplotlib scikit-learn"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "27d0a3dd-e71a-4b8a-883c-40cb5c001f7e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "fig, ax = plt.subplots()\n",
+    "ax.scatter(data[\"imdb_rating\"], data[\"rotten_tomatoes_rating\"])\n",
+    "ax.set_title(\"Scatter Plot of Ratings\")\n",
+    "ax.set_xlabel(\"Average IMDB Rating\")\n",
+    "ax.set_ylabel(\"Average Rotten Tomatoes Rating\")\n",
+    "# fig.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "669fb9d7-d744-4e6b-899e-a69aebec53ed",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.linear_model import LinearRegression\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "from sklearn.linear_model import LinearRegression\n",
+    "\n",
+    "x = data.loc[:, [\"imdb_rating\"]]\n",
+    "y = data.loc[:, \"rotten_tomatoes_rating\"]\n",
+    "\n",
+    "model = LinearRegression()\n",
+    "model.fit(x, y)\n",
+    "\n",
+    "r_squared = f\"R-Squared: {model.score(x, y):.2f}\"\n",
+    "best_fit = f\"y = {model.coef_[0]:.4f}x{model.intercept_:+.4f}\"\n",
+    "y_pred = model.predict(x)\n",
+    "\n",
+    "fig, ax = plt.subplots()\n",
+    "ax.scatter(x, y)\n",
+    "ax.plot(x, y_pred, color=\"red\")\n",
+    "ax.text(7.25, 5.5, r_squared, fontsize=10)\n",
+    "ax.text(7.25, 7, best_fit, fontsize=10)\n",
+    "ax.set_title(\"Scatter Plot of Ratings\")\n",
+    "ax.set_xlabel(\"Average IMDB Rating\")\n",
+    "ax.set_ylabel(\"Average Rotten Tomatoes Rating\")\n",
+    "# fig.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b38df412-c320-49fb-93ae-e253405537a8",
+   "metadata": {},
+   "source": [
+    "## Investigating a Statistical Distribution"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "938e5942-e57f-4e41-99f1-215cfb37d0df",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [],
+   "source": [
+    "# fig, ax = plt.subplots()\n",
+    "length = data[\"film_length\"].value_counts(bins=7).sort_index()\n",
+    "length.plot.bar(\n",
+    "    title=\"Film Length Distribution\",\n",
+    "    xlabel=\"Time Range (mins)\",\n",
+    "    ylabel=\"Count\",\n",
+    ")\n",
+    "# fig.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ff4e9955-baf4-48eb-b032-fbf55f439194",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data[\"film_length\"].agg([\"mean\", \"max\", \"min\", \"std\"])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1b14c433-c3a6-4484-bc0a-26825bd1e870",
+   "metadata": {},
+   "source": [
+    "## Finding No Relationship"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2bb83374-347f-4cf6-bc21-8180a003371d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "fig, ax = plt.subplots()\n",
+    "ax.scatter(data[\"imdb_rating\"], data[\"bond_kills\"])\n",
+    "ax.set_title(\"Scatter Plot of Kills vs Ratings\")\n",
+    "ax.set_xlabel(\"Average IMDb Rating\")\n",
+    "ax.set_ylabel(\"Kills by Bond\")\n",
+    "fig.show()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.0"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/james_bond_data.csv b/james_bond_data.csv
new file mode 100644
index 0000000000..4a983b2201
--- /dev/null
+++ b/james_bond_data.csv
@@ -0,0 +1,28 @@
+Release,Movie,Bond,Bond_Car_MFG,US_Gross,World_Gross,Budget ($ 000s),Film_Length,Avg_User_IMDB,Avg_User_Rtn_Tom,Martinis,Kills_Bond
+"June, 1962",Dr. No,Sean Connery,Sunbeam," $16,067,035.00 "," $59,567,035.00 "," $1,000.00 ",110 mins,7.3,7.7,2,4
+"August, 1963",From Russia with Love,Sean Connery,Bently," $24,800,000.00 "," $78,900,000.00 "," $2,000.00 ",115 mins,7.5,8,0,11
+"May, 1964",Goldfinger,Sean Connery,Aston Martin," $51,100,000.00 "," $124,900,000.00 "," $3,000.00 ",110 mins,7.8,8.4,1,9
+"September, 1965",Thunderball,Sean Connery,Aston Martin," $63,600,000.00 "," $141,200,000.00 "," $9,000.00 ",130 mins,7,6.8,0,20
+"November, 1967",You Only Live Twice,Sean Connery,Toyota," $43,100,000.00 "," $111,600,000.00 "," $9,500.00 ",117 mins,6.9,6.3,1,21
+"July, 1969",On Her Majesty's Secret Service,George Lazenby,Mercury," $22,800,000.00 "," $82,000,000.00 "," $8,000.00 ",142 mins,6.8,6.7,1,5
+"March, 1971",Diamonds Are Forever,Shawn Connery,Ford," $43,800,000.00 "," $116,000,000.00 "," $7,200.00 ",1200 mins,6.7,6.3,0,7
+"August, 1973",Live and Let Die,Roger Moore,AMC," $35,400,000.00 "," $161,800,000.00 "," $7,000.00 ",121 mins,6.8,5.9,0,8
+"July, 1974",The Man with the Golden Gun,Roger Moore,AMC," $21,000,000.00 "," $97,600,000.00 "," $7,000.00 ",125 mins,6.7,5.1,0,1
+"July, 1974",The Man with the Golden Gun,Roger Moore,AMC," $21,000,000.00 "," $97,600,000.00 "," $7,000.00 ",125 mins,6.7,5.1,0,1
+"April, 1977",The Spy Who Loved Me,Roger Moore,Lotus," $46,800,000.00 "," $185,400,000.00 "," $14,000.00 ",125 mins,,,1,31
+"October, 1979",Moonraker,Roger Moore,Lotus," $70,300,000.00 "," $210,300,000.00 "," $31,000.00 ",126 mins,6.2,5.7,1,12
+"June, 1981",For Your Eyes Only,Roger MOORE,Citroen," $54,800,000.00 "," $195,300,000.00 "," $28,000.00 ",127 mins,6.8,6.3,0,18
+"March, 1983",Octopussy,Roger Moore,Bajaj," $67,900,000.00 "," $187,500,000.00 "," $27,500.00 ",131 mins,6.5,5.3,0,15
+"October, 1985",A View to a Kill,Roger Moore,Rolls Royce," $50,327,960.00 "," $152,627,960.00 "," $30,000.00 ",131 mins,6.2,4.7,0,5
+"May, 1987",The Living Daylights,Timothy Dalton,Rolls Royce," $51,185,000.00 "," $191,200,000.00 "," $40,000.00 ",130 mins,6.7,6.3,2,13
+"May, 1987",The Living Daylights,Timothy Dalton,Rolls Royce," $51,185,000.00 "," $191,200,000.00 "," $40,000.00 ",130 mins,6.7,6.3,2,13
+"January, 1989",License to Kill,Timothy Dalton,Aston Martin," $34,667,015.00 "," $156,167,015.00 "," $42,000.00 ",133 mins,6.5,6,1,10
+"September, 1995",GoldenEye,Pierce Brosnan,BMW," $106,429,941.00 "," $356,429,941.00 "," $60,000.00 ",130 mins,7.2,6.9,1,47
+"July, 1997",Tomorrow Never Dies,Pierce Brosnan,Aston Martin," $125,304,276.00 "," $339,504,276.00 "," $110,000.00 ",119 mins,6.4,6,1,30
+"June, 1999",The World Is Not Enough,Pierce Brosnan,BMW," $126,930,660.00 "," $361,730,660.00 "," $135,000.00 ",128 mins,6.3,5.7,1,27
+"August, 2002",Die Another Day,Pierce Brosnan,Aston Martin," $160,942,139.00 "," $431,942,139.00 "," $142,000.00 ",133 mins,6,6.1,2,31
+"February, 2006",Casino Royale,Daniel Craig,Astin Martin," $167,365,000.00 "," $596,365,000.00 "," $102,000.00 ",144 mins,7.9,7.8,3,11
+"December, 2008",Quantum of Solace,Daniel Craig,Aston Martin," $169,368,427.00 "," $591,692,078.00 "," $230,000.00 ",106 mins,6.7,6.1,-6,16
+"November, 2012",Skyfall,Daniel Craig,Astin Martin," $304,360,277.00 "," $1,108,561,108.00 "," $200,000.00 ",143 mins,7.8,8.2,1,26
+"September, 2015",Spectre,Daniel Craig,Aston Martin," $200,074,175.00 "," $879,620,923.00 "," $245,000.00 ",148 mins,6.8,6.4,1,30
+"November, 2021",No Time to Die,Daniel Craig,Aston Martin," $160,891,007.00 "," $759,959,662.00 "," $275,000.00 ",163 mins,7.3,7.3,1,14
diff --git a/james_bond_data.json b/james_bond_data.json
new file mode 100644
index 0000000000..852810b38e
--- /dev/null
+++ b/james_bond_data.json
@@ -0,0 +1 @@
+{"Release":{"0":"June, 1962","1":"August, 1963","2":"May, 1964","3":"September, 1965","4":"November, 1967","5":"July, 1969","6":"March, 1971","7":"August, 1973","8":"July, 1974","9":"July, 1974","10":"April, 1977","11":"October, 1979","12":"June, 1981","13":"March, 1983","14":"October, 1985","15":"May, 1987","16":"May, 1987","17":"January, 1989","18":"September, 1995","19":"July, 1997","20":"June, 1999","21":"August, 2002","22":"February, 2006","23":"December, 2008","24":"November, 2012","25":"September, 2015","26":"November, 2021"},"Movie":{"0":"Dr. No","1":"From Russia with Love","2":"Goldfinger","3":"Thunderball","4":"You Only Live Twice","5":"On Her Majesty's Secret Service","6":"Diamonds Are Forever","7":"Live and Let Die","8":"The Man with the Golden Gun","9":"The Man with the Golden Gun","10":"The Spy Who Loved Me","11":"Moonraker","12":"For Your Eyes Only","13":"Octopussy","14":"A View to a Kill","15":"The Living Daylights","16":"The Living Daylights","17":"License to Kill","18":"GoldenEye","19":"Tomorrow Never Dies","20":"The World Is Not Enough","21":"Die Another Day","22":"Casino Royale","23":"Quantum of Solace","24":"Skyfall","25":"Spectre","26":"No Time to Die"},"Bond":{"0":"Sean Connery","1":"Sean Connery","2":"Sean Connery","3":"Sean Connery","4":"Sean Connery","5":"George Lazenby","6":"Shawn Connery","7":"Roger Moore","8":"Roger Moore","9":"Roger Moore","10":"Roger Moore","11":"Roger Moore","12":"Roger MOORE","13":"Roger Moore","14":"Roger Moore","15":"Timothy Dalton","16":"Timothy Dalton","17":"Timothy Dalton","18":"Pierce Brosnan","19":"Pierce Brosnan","20":"Pierce Brosnan","21":"Pierce Brosnan","22":"Daniel Craig","23":"Daniel Craig","24":"Daniel Craig","25":"Daniel Craig","26":"Daniel Craig"},"Bond_Car_MFG":{"0":"Sunbeam","1":"Bently","2":"Aston Martin","3":"Aston Martin","4":"Toyota","5":"Mercury","6":"Ford","7":"AMC","8":"AMC","9":"AMC","10":"Lotus","11":"Lotus","12":"Citroen","13":"Bajaj","14":"Rolls Royce","15":"Rolls Royce","16":"Rolls Royce","17":"Aston Martin","18":"BMW","19":"Aston Martin","20":"BMW","21":"Aston Martin","22":"Astin Martin","23":"Aston Martin","24":"Astin Martin","25":"Aston Martin","26":"Aston Martin"},"US_Gross":{"0":" $16,067,035.00 ","1":" $24,800,000.00 ","2":" $51,100,000.00 ","3":" $63,600,000.00 ","4":" $43,100,000.00 ","5":" $22,800,000.00 ","6":" $43,800,000.00 ","7":" $35,400,000.00 ","8":" $21,000,000.00 ","9":" $21,000,000.00 ","10":" $46,800,000.00 ","11":" $70,300,000.00 ","12":" $54,800,000.00 ","13":" $67,900,000.00 ","14":" $50,327,960.00 ","15":" $51,185,000.00 ","16":" $51,185,000.00 ","17":" $34,667,015.00 ","18":" $106,429,941.00 ","19":" $125,304,276.00 ","20":" $126,930,660.00 ","21":" $160,942,139.00 ","22":" $167,365,000.00 ","23":" $169,368,427.00 ","24":" $304,360,277.00 ","25":" $200,074,175.00 ","26":" $160,891,007.00 "},"World_Gross":{"0":" $59,567,035.00 ","1":" $78,900,000.00 ","2":" $124,900,000.00 ","3":" $141,200,000.00 ","4":" $111,600,000.00 ","5":" $82,000,000.00 ","6":" $116,000,000.00 ","7":" $161,800,000.00 ","8":" $97,600,000.00 ","9":" $97,600,000.00 ","10":" $185,400,000.00 ","11":" $210,300,000.00 ","12":" $195,300,000.00 ","13":" $187,500,000.00 ","14":" $152,627,960.00 ","15":" $191,200,000.00 ","16":" $191,200,000.00 ","17":" $156,167,015.00 ","18":" $356,429,941.00 ","19":" $339,504,276.00 ","20":" $361,730,660.00 ","21":" $431,942,139.00 ","22":" $596,365,000.00 ","23":" $591,692,078.00 ","24":" $1,108,561,108.00 ","25":" $879,620,923.00 ","26":" $759,959,662.00 "},"Budget ($ 000s)":{"0":" $1,000.00 ","1":" $2,000.00 ","2":" $3,000.00 ","3":" $9,000.00 ","4":" $9,500.00 ","5":" $8,000.00 ","6":" $7,200.00 ","7":" $7,000.00 ","8":" $7,000.00 ","9":" $7,000.00 ","10":" $14,000.00 ","11":" $31,000.00 ","12":" $28,000.00 ","13":" $27,500.00 ","14":" $30,000.00 ","15":" $40,000.00 ","16":" $40,000.00 ","17":" $42,000.00 ","18":" $60,000.00 ","19":" $110,000.00 ","20":" $135,000.00 ","21":" $142,000.00 ","22":" $102,000.00 ","23":" $230,000.00 ","24":" $200,000.00 ","25":" $245,000.00 ","26":" $275,000.00 "},"Film_Length":{"0":"110 mins","1":"115 mins","2":"110 mins","3":"130 mins","4":"117 mins","5":"142 mins","6":"1200 mins","7":"121 mins","8":"125 mins","9":"125 mins","10":"125 mins","11":"126 mins","12":"127 mins","13":"131 mins","14":"131 mins","15":"130 mins","16":"130 mins","17":"133 mins","18":"130 mins","19":"119 mins","20":"128 mins","21":"133 mins","22":"144 mins","23":"106 mins","24":"143 mins","25":"148 mins","26":"163 mins"},"Avg_User_IMDB":{"0":7.3,"1":7.5,"2":7.8,"3":7.0,"4":6.9,"5":6.8,"6":6.7,"7":6.8,"8":6.7,"9":6.7,"10":null,"11":6.2,"12":6.8,"13":6.5,"14":6.2,"15":6.7,"16":6.7,"17":6.5,"18":7.2,"19":6.4,"20":6.3,"21":6.0,"22":7.9,"23":6.7,"24":7.8,"25":6.8,"26":7.3},"Avg_User_Rtn_Tom":{"0":7.7,"1":8.0,"2":8.4,"3":6.8,"4":6.3,"5":6.7,"6":6.3,"7":5.9,"8":5.1,"9":5.1,"10":null,"11":5.7,"12":6.3,"13":5.3,"14":4.7,"15":6.3,"16":6.3,"17":6.0,"18":6.9,"19":6.0,"20":5.7,"21":6.1,"22":7.8,"23":6.1,"24":8.2,"25":6.4,"26":7.3},"Martinis":{"0":2,"1":0,"2":1,"3":0,"4":1,"5":1,"6":0,"7":0,"8":0,"9":0,"10":1,"11":1,"12":0,"13":0,"14":0,"15":2,"16":2,"17":1,"18":1,"19":1,"20":1,"21":2,"22":3,"23":-6,"24":1,"25":1,"26":1},"Kills_Bond":{"0":4,"1":11,"2":9,"3":20,"4":21,"5":5,"6":7,"7":8,"8":1,"9":1,"10":31,"11":12,"12":18,"13":15,"14":5,"15":13,"16":13,"17":10,"18":47,"19":30,"20":27,"21":31,"22":11,"23":16,"24":26,"25":30,"26":14}}
\ No newline at end of file
diff --git a/james_bond_data.parquet b/james_bond_data.parquet
new file mode 100644
index 0000000000000000000000000000000000000000..88bd22b4fb36adc606eaf6eacd5b46d56121e5d1
GIT binary patch
literal 11050
zcmcgyZEPDydY+Y*HffWwBx@DYk?cK1W)x>7?FYZsa9k}Zks?D%7A29CF0HU6R}`h?
zE{`9Q=rl!8^om?AIQRnR;5!tDG{}#jz4S+s25s6O*Zw#J2M6en^iZHd5geLJa43qP
zD1stro4zxoBub?6f!HQIyEE_1ydTdy^Ugaf-%yeQLo=_QVt(5jXG8`KAoRoDr_UgS
zVs%5~SV8uQc4#T}LcLnE^bJckXeHE!#o_UsgX)r2u4$#LR<WEP_C5rJd2`1#fc&-_
zNViF}eAY5;t>iYTDcUdi))DQOCMV$Op(gs2a;2zSCRo1%rY+=ZrlUmrW!t3f&*^|b
zO`=5qx9Na%brR75@5tYxfF(W{Q;oV>vHX}0$icgamc6!h+uKNXykjfTvOM`W$S(4{
zNd31xtYs^<McndH1J)TWH*p3x0@Q#!3>87VT1QrRUsWh*iUNa}0CSCFd`us6ia9mx
zL*wTTOygJ>>2;nZ3S&(Ce$aSW?}4X}ve?+?l^0~|<-f{Q|Ksn+AA94|EYRI=T80_B
z%ZpC+xtynyny#r;jp-Tk4SjHW=w}x9OSIei<x*T6cn2{(2p)a#LI~Rbe46=_)BE1~
z_ufxlJ_Yod$|O5)GEfUw%o3ZdSF1&p-7VHO*|@o*VUI>kJ-<;j3R>kXw3avPMqaCA
zRb4+1%~i9`E*N@)jTd(`c6qm$(=Gvd!C>dK3Y$>3v}&#KSe0GUauuxxugVS#8H6D-
zMYUua`6{baG&XEjv>mO|2Xsr6SB*RyhtV@d?GZ%P`!rx=*zVYCn;J{qc4`J2sT+fi
zOU|WogH3OmmbYf|Y(gVT%ruRPx~)|Ps1G=^!h(JkcDA8aEpJkfmhoySgNY3+NMTb&
zZI`W?tja!B)b;+SH^B%nl$}u<da<xstKyX!2YrpIMomypP;uMKo4^bkzHFAvO2yn|
z=dt2g)#}64!^@yy+N|h#Hd+N-YwWCH)(e|d5)WV%!>qxQ{$xRI;I$i4t3|_PlV(HJ
zwSFKh)>WfcFR|tZyJYHWPCE_6rR~NBfK94pEmx~(&F#W27fTw}9yoVdhUdF@#@Tn=
zX5jxN>+!vFhwIUjFn2&0UX8EYhCZ>nUwO#=Z)DMbMQL5v<qJK`CsZ8PDUKrFrC!Hz
zV@XpDHe?!xR%u{!Bbr$$Xlz`)sTo-U-qNPJYxF-Fz-uyT!s28TCM=?nbM}RW<SeCl
z03JZQ0nXHGra=vOZWOgjPGf@=vudaYRp(|@qp0a@sG=4NfZ#a89ofha9p&J(w~q&@
zgYo7@?zN%kHvi=pZ@f|Z{BsJq-x@pwj1IyICwTpJ@6fBg?$^${Z};Qv`^CJw!gQyH
zd7&rHTp%#LNZld}qHbh0wS+fvP%~<JgT&k_*b6(RQY#wNg~4UBVb)Y?>RJNKuU8s0
z42JEN@1-Wj6Cn$<;%2R0r5<&LinWTV8Ps4rsBWoSO=NYwidSe(qa<rEk#-c=;y!c0
zjAuMYFgw+h=Im7xA>izMx(N|&>l+Pe8@qS@?8*~Qa2ycbf8;uZ$&O)K52=;)L^wj=
z`Wb=iMW_4M42J6n+pg$*cAB|E?+3U4?TzCN&W;H_j`#UFUh+=zJZl>q6Fppj=Q*C|
zU4wS7zzNp}k=-Y8K6uj}DLjs7Q4HT8b?A}2oaZ{UM1gvqqFpc29$)wxvio^Xx_%AO
zUJp#Lg8(@=j)s9KLe)2tr#^wB$G3-A$;0`ueBm;O`X8Sj<9(b*lsVZWP=D%R#zZeC
z@g7d}`z9IW^l`Gpb3R+aab?WM!yu6pBzfe@AaIa;-u`F%udp)I0>H!Xx<YA#5)2dl
zBMcI$5BmHbPVi5@jyymN$O72t$3}Mv4SnnwwxEdv9^>o>s19|*B!KTr0>dA(hYqx^
zEUiaiUsZ|oeqkH>*y8@xMfXoHVCQ`$ab2DIBP(<Fz^UJ-TTb=LocD-R{Q*vH8bb}D
ze#^L35Ir#l**yX$2CpEyAaFhxV_TvFBDFx#BTKa4qxzx3*nI*QxPBcn0{>(ZIeusl
zfWuvn+n7F4z&>V>Rgk@ySHRDCffwr)IUn)z<Vy(2^B)4m#|cdz2W)@fk)YXfF~Hc*
zj7gwv)5jyQlm*U@eLPu2;~q)a_p$4W(<}S1lYN(|aW6Q}CyN~K4^UUo`Nv;%asnR!
zn=MxAVcW~&0ly47zyc8^7ZdOU95NK2PdwS(vY+#{x%)i0yTy~dzna58e(ccUXUQSg
z=JVg!hF&@4e$(xK=UXkGe-)Wsz5d)O=I0RTcoOKI>m?B$D-4?!D{4E3L?0Z?5`M_n
z;o+UUhETwF5n275IC&8vfB!|=jx2ky7a$Hu%=c_8Ee3onY-E3b2^ta)4dl7rhnQd5
zc;sVP+JP+3A>n#Iq9t#C(lP1^Ir<ULEZh2#==v_MUtNLu9(az6e(%0EUAEU*b`1NR
zDC>mAf##ii>Z4a)8`^&NN#}>J{nPJ3ulp}14k11ltmg}m1dWfeV0ra%vbEkiJ@i?x
z`!?r(^KlIG$)dU<`^#SDJveFI1lbQM&I&RGfoDraqiVAwugi|4Nhjdva?&2rVn;UW
z8ZGi8mmvUJT$U&jN20Xo8*z?Aku<{7lH?kr1=(c>bm8Ig00Vwx8F@yoLE)V~iLma1
zkyU8*Ijs<Q$f%>}AYo4UX!!Q+fvoLUKYE6bVRU{g9HMhJT+~bJam^^yHVHESMGyU9
zuls%8{qZD5rkjASn0!Dnw*Zr2f=L-k7Rov@jVu&>aoTc@mM%H^?8DPP`7uSIM;uQ3
zBh&BRh3W-|6*(Q_@b2s9k;{P#JLZIO_;+dgxW!KEevcDl4nODgP|tW5Ds&C&_&gt^
zdjD^Lf`e0BPHm+3HtxLrz8fFb?oYkL%$e2&!J+IF)>o=pWj&gh2@)LsvUlh=J?@`-
z+_$9RuOYT8Hm~$Be+Sr%5o~TzG`8J(k)Xp)+xo2RG{6P8SiyX!{Q`l>`tbAy5C<Jj
zGz17Sjy`%|+Oj|cUOWut32uNYVgWJNv_yU*7_n()<}jCVTHn2kf9&*rZGa%wNd-*U
z-#<i*T&vCqAF(eDe(U=a?>+qtk5dr$udg1W)^~tfvSzG9B2R$(tas=qkfF)$cl-cc
zryT6BPAcjO+zloWXU-7V#_1lo>>)%s&Ry#TP4Mrt&znCm`bg60wC;~^TKC5c!CLO5
z0+Yk^^ZC)s-@8rU8ha6rB=?)whZ(xHJgm(mu-H77f6z1Z8Rh=LlkT^#fq|VoPmt8r
zz<=yv{sC6T6=LG+6iq{@Kxb{I;SH-{5DEju0_8LmD-;UKB`9_%15nOEaX>i(WeUng
zD0n6HIjq+%5R?$YnLqw@Zl|ec2Xa~gTJpo%cT%CNOBz#zkh^s2d=h%yw?l_`ox#_@
z>iR*_{wh6mr`P?jiu-?l2N3JzeuB(yh`HYPBIl`UZc{6%j1w{T%RL9z`^zXk45|=X
z^NQ6@A$N#&!jWvbz2hJYYbUm!)a~@+$4h%(dvM*Sp8<uBh8x6STE}LBPYpmmSbEK7
z8?tD~=Nfk1y<Z<X-1qsydVlVB_w+jCzTc_2`+=l__ca^356Q#>JDDHkVfG--lLr%n
zhkiOc<a1kxJ{95Xql<H%D#K?+wd(x9@yuuuK56c)=S;m`GOD9j*>68Hx(zg_jaF3n
z@;S<}qlQ}2fMC>h9a_~Id|!bkPwHkFs&FmDbPd;qXMYzOO@`})yVl}+l+6ZwfXc5Q
zr8V_huQke8-e}z@=FEIkg?g#nIOs65Tkts$t5(u#YF@3WF#MTO&4A(X6%)^0Sq@JG
zMxSj{=BO5<tq;tY$q`lBJHC-V7_MhIP^)F*DEWlgDer)MZ>8a*yi?dd_1??c|A^IH
zW_$0wmA(J{rBiNu&%Kq|_6eX<?6J;!EBV;XxKnzU0rysew%cc?^kbd(R`S8!1>g8O
zWp{KRlfI#wYR%`t6OAL$q^+YZoOEp81OBb6(-&yaHsT&Dv45@U6yDx*OlZ;QYWD&8
zi>yAp7j%j|+V>5Gl2fCisWr1gg1KJIR@6!Z$MSMR#eZ+Y3cw$nszuYlRKYXJPYR<D
zVn<t|+d9QbVNx7@7CG%oGP#hx+Pr=^?_8L|zd#|TD9R!f{Ci4KJW8;jgcYTrgbIWf
z3?Av<#l+cz{$OFQ*@h?KLi(eMva7&6coQb@CX?W~3MII^n)Yt5W)h0BphTeUkCycM
zS|sJki1Rzyxl}D{B#H~gU{-6yDk_YPZkdIs5!=j`@_MwmTZopto7waV9#hY!_p0%b
zQp`!o&783aG-bEd-pPfczUWL;YPI!dJ1l3GFprijT`p%!NnMMiZelrUsanjI!nL&}
zm>cm5*~o4+8j6+FbgH@*mg}o&LC52=Myi?(0Usj>dVy>~=Cw?a^hJ$ST}{vLtVLFe
zST>BU<>vH_{G7f^_=aLTtEIBODlInq(<y#6o!rbvX0c6xN2<Om%G+SOL2TDkE6F17
zi5kLD-4Ag(&?~CP^lT)xnG>6`*Gf9HlN$#%g<?x<={<clGvCDW-s?|%vH=)_{|@!q
z7IyNWOVfXAWzb<eBkucADK4jFQ3an8Uq!;O9>O;>Qqr3P48f<xeA-*am;ip*A0R{6
z)lzMkmt^>Ba%w9dBK@_sOmY)=@T&)Y+>_%WjP0S!#gbfKYmV>mZ*)7hlPxv<lY5Z*
zgyoslOl)I$Wo_;xtcc#n$2}-N>Z#=npKoNP`I{%{mrBiVB&FC+PD(sbf2Ksaf!BJw
z>@Mp+la*q4FVE#l^37a>td~|yns48uLbjxDWyR!v%n`DgptpTZX2sZd*3$EQ69+-h
zN5T--lA8zdVUDjx=i1^)C>F}6lg3(RvG7!Av5=Tic5{twf>9SePaON8)?>1ySF<TO
zu?BG{A1R!qXGBf!)iV5^4)K{+oBQcO;Tg=A@*63LWjS4rEw3a)C#}iF%$kuAQa9IN
zZ!N6|vx~(O{a(sO<jwrdYRj*11|0MIT4`@*HM1zrf1Oy<CV$09)-ytKC)<o=U1CpI
zTodF}PE0j2LX6Mq@=8|ZPuxq#^yv~C*Q!}D%+GIiJ#S8m*KnRD;cV1T+~>>ba3del
z>uToYeGX^Xq1?`Mu$(o%9*#>QtjW3gjW3SfwQ@GHcQeC(aSZ>ay0!9%##%beXQgQC
z?A|M{LavfCw#m5#=RVY9JNagu5n=t^RMT>uoa<Y&e0)o(CzfJxHbD+^aL%mhIb*(@
z6+MJUqUhO+Z$*n6%}fmvCq+r&^eR{gDauS0=U#Q3mPHGYb_G{)JBHgg@Pv>DkKe$L
znf?4tQT#WgsVUrCj1sOmkvmNFU=~i@W{=>gD2bamX~YAAWKwA6iDr8?1kzv<p^_?Y
zHuJyWJe+4dU|r4;@mTR)1r!I7%_I{BHu;5b?(>`J$`7oAq3wHqDIf7}q#|++_b3T}
zOTVb1-+(%?FF};TiEg`nGnhKtw$FHdJ~<o3`7h|Vir>v&VJ0!PGc^T`U@%EYIs7E5
zkfsvHuVb-N*~Rjww)X7_H|-%4+VH_x2D`<1C4lEQwp#YgHs=Qq{YN+{RXqRbdA6(M
zVA53T20V!UE5!Z||6&H=!?T?5o5k{;Q1E=rxMeRvqRn2i{*LD$Wd0nPzk6&xPWs#N
zBKDK{WKyVr$BW1GjgUT~I;oKbGTY1{F`<FS?|}*Ao&o;aRft}|e1Fou{>S}ApjatE
zKA#TXTwBB&WwE8-lTRWiTUIOIscW@~T)8|!E?jKuLd7<(TCThBx0)~ghyK%r&<*%s
Gvi}c^zcEVy

literal 0
HcmV?d00001

diff --git a/james_bond_data.xlsx b/james_bond_data.xlsx
new file mode 100644
index 0000000000000000000000000000000000000000..1e042705fc38619b41b62bd98b1c1a807c061cc0
GIT binary patch
literal 11269
zcmeIY1zQ|j);8QofW}>eLvRi5!QI`1ySqzp2m}opg1fuBy9Em#92$3d`<$8i&P>jH
zzu=kb?%G{_?R#BaweO{SDat@WV*+3RZ~y>+6kv3kX`v4R0K`E902lx`NF5P-I~P+s
z7XwvK2UBM~Mh{yXk{oDA>TCccc>e#6|HDt9EOAu6ml;*;R`N+?he3L^MhK4mBxn$w
zR!N|%FJYj>SSQQU@--{s5mop*mKA3;`sAuN>-o4vjh$^nQ20QrGGbKVP?wrM0Vh-c
z;4x(<4qm*IwiYNGlR$_C&%hwYEFJLGv9VW~O?2~vbQ!({7PdgZcINV+I@<a`Gh&H$
z5%<ta_lCUs8XDI~@hs~0G{&5jC5^ZK<u-#9bQGEQDz=+`z9Oln3XPF+v(rP0Oouad
z)BAZtW5_k;(71NwpA+jatsR_1a%}iD#gSJf+5>Ucbe%rBK3<*FpQEl6A6huDEDRWQ
zvV;OjgJu>1iq=te*yXHtlfHd|Sh=#JXFVi8A1OC6-uA5%n6zZY#+k_DlG)O4<PT<v
zDsXes2Kf~Z4L5OhDV!L;^|33MhTVY{yL-jFK|5%<>=H&D?joh|4LjKwI^gv_p8BN|
ze0rXI;LrL30|30fLID*2LoMson8~leT$2TB9RgS_4V+AEoS7K^IR8%_{}1cnzukIS
zyqrQWGh!%6@+oZScK&A^s<4dv2gz1aRlfkKRh0UeTnd7pom6j8Rq=zNB>da`o<>%F
z^2Hnuk=|^vl|`Xr@{%{Wmxrc2IJ&~pzH>?zcP!iNLvx$Ip1(<zkoKf@YmcQZZ7TXM
zGrUeNK6@@&jXKGwfe*yUe;bO;pBkt=Ag8rvbXNf}FRXG>9$MANnSGcrneP81x!?dv
zFq~WVcqSEV$l1tzslsQ-hV=R#Uroh=+p@|i%ZZ1~)4;^0>rynm6XV&3K|W(hnT!qn
zj&)LEkTUz)U%QU&d^FRuj}zEiI&?N16h&OL2KG>YSCU{9iLi9Ag1~`Q2nGCPJZzZU
z?VYTR?Cq`p@LPGRathnbsO^<?uiY2?6sHo><jQl(Q|j94So99Xs?DEQJfx1xPNvku
zUpuz*XcF}`!_ij~9JAKP+Qydd-%U<o{1B(cGj>8Z?4wkPh%3cif9|-DXJJhq`D7-2
zfotE~y%!8xpIDF<WK8rD1(3)^t5`=3-6F|&%8y6THbGA+A7p4VUypEx?6R@Y>~Ty!
zsiS`KlMm@*7tRw5`kpM)eWzK?x;L{xl4d>!>6;MQ!)C$#2&XH5ZLH-X`|FJmz398+
z2FQMD^Jx>xq=G2Kp0zl}Ws4>e4@rPXDK}78LgH7DrRm&E7NE``K_K!Qv;ZkA&Eng=
z4P!|{gG;JSt0wdOUWFR?Tg^>6Twq7ExR7>|I+^4e)pU!u9RnYiPGt1@j~TH#YQO1K
zHQHY4+yVV}Jr@)M{LJ%d#BEciEVN=UYwC;ku2q7Iqn;(*0m~@wN9*&F4X7<YSn(bj
zB&mh?exXHWY1#Cb`Of{sOF{|<D?UQj!mMJYqIyU_fHQqOA@r#hm{fa^oUgj4QvTv#
zHhyfzL#!gRCn8l_j%Icv{^d&Z<@LMNh_1Acq=;O-ey0MEc|j?+wRj$GA>mwM=$XMc
zNLr{p;b$yQplZU6E-T@e`%BBk(*!rpE3d-dtRDyN;`*IpE&8BCr@52sux%MuuRuc=
zToy5z^wY@WY~$6yNTTM7gM#xo5?Zkf>22;sy{z<gq!>{Do8#rB_6_SxT3GX(@!+@!
zZ4o#<YRqL0v({M{XFYCWQ6rTp3?Ni^tKV&Klp1_A(DM2t`Oq3m)Hy`1<M=*2<0KMn
z^b==d$pCP!1aDaSxUnJ?eSgZXB0l=d=T$tf__&hrar0<1o02c-s{`3i9CAKqV4D7&
z$AJQgDVJdWwt%^e4}gOJ^Y|b3{@>aBFWV0R4#mLQ@PGR#Q<jtI1FJT|OBl0zx*HbS
zk_!{rvDy&|+;APu$~)5cepl-Rv@Lp?3o=Yl_Mx7j@j<s+cH}K6jO%W?qDXXTFAN(H
z?;HE^%W)_;qmy!?Ac;2^=*Ndgr6&l;Y0enU0`WuiS(seAchr=4VYvllqF2o`p=?$Y
z%&x3f&QpXVVB0rZw-fO2N#(dasIIY*B#p-G*K4!L$_>o7AW!1yOFW<yACf0vdVh|T
z?yg(x2JWKm$xP03!n!;60rA({QW>HWc7C5w7m~0c31WYmc;{a^sjX_DO&8(E5t`1G
z3;NM3klD`g;QTsxrT<PDZjL|_M{oo`#0UW3f@l2G^f_CYnz}eM{W-AwVFNSbb?kdc
za6>^U$AYM*Nex5=F|I6H$*IRiO9w;;8Zz`#5Lq?HouJ$btF0KVS!MVu&rY1R;b(a@
z6Q~8L-1qqI<kCV22{P?t`-6|h=Asdox_fP`_^d6k5}?9H&V=%6It@sVAm|fTZ7+ku
zXl|vTtqN<aDJ~V<(xyR$R+EZ`uFG92wQ7pUP+7;~gTT0DYup0ryZ~781^7BaA$rwS
z<L8RRdTUE*-C&i~iUn5*Ts3kdQo4g%q(pSenR{h|Q5>v?wSHg5p^2@`jah5cv~vVX
z$`JMm%#J7%x1#%*m#;B+I1)4Yucge6-?SEo90I6RFFND5y1yi47`FTOgi2^GGNxCU
zW=(_kL5CZ>$Z{@L%gw|*nLFqTTuo%yk<k-dSKN3?9GPqo4~bQ-=Du6^TS&C1M2Zvz
z6g$oz$7ty@wiQ1~{-B4Gyqy;|cbp?eIt>jR`@DbYM|Zg>dfy-a7QUn6sdPyoP&b+A
z8peW|f@1s@Wdm9q1FLlyP~7?F0{(eQOk1%#;y@MiryTMoRB7<xJ_9N)E%c8lKwAa~
zWMWf&Sbp)fOlWBO@s;6gq2WSYycr6Uh}Z4;<KyGr=Jn;Z=j~-|Cy}3@ze_9%v46+Q
z-Px<J^Za)2y50T5%}Jv_GKkn7Bq-1+IAN~#eAnj9%lqne(@}T6(W}#$wbxo$x%YEc
z=gOiiOeMDcx@d0OkRSWdv5rXQ+M-;doG9~Jvsl8Of8mftGd9L6qij%}e}ETFMA6{1
zNmj}CLV9iI3Lbmtpxs`Wr)Uc96Tmw#{P_b(j~`}ucq1g*u{_DvDuQTu*kOFh5njiZ
zOZ~Q#aTPfUQ#X%q8ML1grU%Fu!Ka^;A}*II<a1z3vd43-kZ2B8xE*icR4oo1f0!5|
zAAV*KA^zv?ksTEE6sbE?rPcOZO!uNSxW3jC6^kuKhA%#Yn2cwR<w6!efuAzk+fXt5
z@U|zGs24fkQ}e;_X1$`9sjSDJxhie6-!hybP#BP-RyHVn2l~L%!RWV$!8AaAX~-1H
zlVU=JAexZ*_2Ye7MvyDJaStpnhJa>*<%g{f+Q`=1tgX)gb{gF+h8r3-$CPBr^jx7l
zTRPN;DWE9X6(s3iRZE{QdoNX1g&UtGqT4&4D)rQ2Gd)aCkZ;rzI&c9_wBh&-nJF@4
z>N!mr_dMK=DtVkrjF704=HQTXN%L}Z0}L-Yaalr1{6%_Bmp4df!<s^g9960g2W}V{
z@?1$GFkF-lHQtp*_d|_7i7<za(FXUD?uqQZ;hqUbnF=xbo$WvFkM8u{8z)YhxODu$
zRXO+_J7p601jy!e%%OhQ^x-?hN^aPg?ujngqboyTTY5^8>Dn{)Lp{y#r!*(}d^(ud
zC$fa1=#DA&La+Rcqk41rY}<47;KDsqH+JJw3B}1>oqG|p=;_Hht?%n&Pat?}Q_u@>
z4jg+<-drTvTsRp&fzl^@r95-;$U63%rVMI`r%vkb$#C>BZlw|0wM(=?3V7ik)M7Ko
zA==<sjHt`+HQ@4f$v)XNiCgH{9rN?YVlp;Pw++3iFH3W^L~81;#m^raY*!?htJ|vw
zmhh!emJ6h?mn&n}OKZ)0;TI75jL`(8UC!VJej#0GP!Vi_PsD0uWB_uO*(KGqsYN34
z!TltIij_W(DOVOPQ-KG1=bQBauZw9)<vX;d!gR9X#t<<^*H?{n)el?hgjUmN#EVjm
zl&vI!>)3NYfWLkM|59??oNA2eOm*1F)t5fVhc?IOK|szd{OPl90kVT>J!r|7XD!27
z0)C9Y*pM#dCT5N=$DT+4aCryu6&AHiJjQz5+N=<e?B)jFRfIOi%`!6bF$MdJ-RCQt
zfG^*?`;qOvgsgKz`FOdd+H|ez_E%+<mY2trX!OtchHf*LiuD6ib0If2osWm)PFqwH
z=Z6@}=|M%`7mG+2OTL%K;4d$i;Y7yZgWog_Ry$T^#Ia+MXaP#(Uu&%ru_hQ9I0;c!
z@C~!H0qNCW-0UVKr@vycF<V<0sxa-lSAV`Ke?KY?-A0XIRvQtyd(e9=URIV^F%$G7
zwH42B!L~~>9f~>r7A`t)7Lpu=$57u4o`bx1cC`CCI!YXR*TgkCz)JLz)j3BsX@1K5
zb|*C6TiejiDli7$a?i{pn<c(cZOl6p8CU5r@Z2nT@S_RI8+na@FKFZ9QB!gkPCTse
zOi|auxWg-|k)AQRO|07cYIS&c%iOmr9vrtSU8@QZ&cNHd(`ARqE_H7-T<)!UCp(Ko
zte;7%&`chUxr?i()D2EU<&2ehQ=A$Oh7}uKy4_g3jQB(bb6u146}x!)X3+r%9&CHa
zLM1gLkH-RXDl+;!0A~o;-F_(MQ31mR-!A$m%*%-)ShM0yM@@E*6E`T2Ocu!S7xeLF
z8NXMAyqs_KlFiz+XS}x@#cH)@Dr2Rs!G^6?7VBm}4Vz?#e((@2i_6$K+u}~^2W95)
z$?Fk^Z=aIGAwdu4a}7^hymqtM0qmHONOh73sCaxIbqt|Fo!5X=fRGuz7*?DNi70G3
zkV!zSDwVrE-;f6Pd5j0Wve@}B5o<Rov5{}zB4B)#vb>y!rXg62czg>g*6bW&Yzu0!
zjJ(;~dj0ft%{m&)tEbxZvYMW@_=^SIUl8dRBHB9a$~N;;668xdeE7}F5XM_afnUVI
zD^QfZqJkWahRbgBQGj1?Ojlu+$>8<PAMwPW?x==FQdZ$wj$V3lj81(>N{+5tjdkih
zr<yYLi0ov5v-AamO%h@fX8eVW^o4WxSoB<9;v89=RrXfh(-S(b#QKDICtoLZD;GI?
zeIN3l5`Qma928JCnSrx26@ovii+_eGE*7S?rc8gH|BO(MwZ`oTI8i%r_IXjg73i1Z
zjqtue$s})aI2tWVN4_oAvr0j8ZziGPZNVC@77EO<oR$e(^P*mckqpqEDRfNFkqc}S
z4%?B|)>gHlf_cCpv|+g2ewuU$ZSgw!Ffv7o7JpHOrOKoMDOwXJ!4{>{o#_Xf@e0W6
z(fWipDM|Mg6;F4?=e51mLxhro67I&_392zjwAjbkR4lYA`j=@|0^%A{vt)IU1X`si
zBr(L##PTwA+L$EFS$ZKn`M~3o&A3qLYxZG7XX&=l4Hgw;rcbhOEoS<bK2}W^m7qD1
z@yce4jA=uhMcgTU<5Pq%(xmm6hNs=dD6`Sm>n7-bSCD+naB`HYP+hr*8l#S+fQDiw
zTiULDIdT)-0l{1!e&p7gY3C|F32?v-Do{^m9oM#RU(TAL4?O-Mwwx*5uIzkH`CyH}
z%DHml)~+>V6oDW2tgX{ksexZ#t_Eu_gl%BZ^<!BlQ@*#GAg-Si`>dUATztHrK(WVy
zLtDr??8fWOHJ-`P(r26w<g;sOh;O+h_-51jT8N$n$^F`qAm?eQ02tOXi_kd=Dv`Is
znC=cdsF>C;9>E(k1g)4OA(Z0?!-`Y7^+71kh<Gf8w}<z)m05yf;19Ro-SOR~!eA^B
zq2SZ>j1$M{20f#_&;5zHzuz;<!}b9u6S4p1;3(_M4`PA)Uwf0!LPOcjqD&n=7b~??
zOdStbw;&?#4IN07kuw3g2+_tNwB<dTeKW*uX?d6}AKnLG!31&!z!v48Li+7SInYc%
zH@#_~l`h-kF5t)DEuj_)I*a;T@4a|DPnX_=Rysl@gq?*xCBp5X*0DL`fa$8hK$yT9
zVFq`_$!F)HwApMIn{}yh@?E0d)E<`MaN!3+VzjO4Q=<IOdhV9gO*<kXr%H1JbJp<!
zgj|7a>vbY3XQO?E@0*sZ$4~X<cE<{@Ik;WE#G!um`~<?-{d&$rM3?a(dE+=T0@E3x
zwuNzFNY=wzL5JnR^Da8qPBic8q?tizJ$}~Sut-C{5mX~}NEVVqPCTCe^^(;oJ(dS3
z?_4>?CNr{#vI8fKnaf|{bEbD{7VZZlxM5S=3R2!`db|>L2pjk;c?p=dAIK?MmVcJB
zylF8SqgLH^@AvTHvF)DTk%`E}p!C2yHPG~EJm*>=M?H#yoosD+tT=^vy>DryPnp!V
z-Ft(bw&Q7F)3W1YnZTD9O;`jZ=gdDypnQw1gn}&xWna*=G?hqoR!@D3%!s{s{2{0`
zwn!QoJwqf`kDc6r9$}_hlskoaCDru3PdrB5IG5D-agKzKdXtC^M3QB0o+c?jMrt>s
zqf;@B-}}qsm0LoZn>M)pI{B(rt|~LWTcXaMld8N|#G!)c(^P~{KT!tMg9}=FQ??p_
zrZ<XQ3pAscacgwGoMTA44r!5m$3+$rTelV^P=Ze-XKacuPDFgb4Z<W&YGP+!YTR(c
zrb=3xPp(S$0@=2)5!&tP&v<&15o)Q+%O`)&Ri7%WT!6ydYQsYOSQb)giL9T}a^6cH
z+WK7)NN`j5t`_*CnKS*Rs;oyYr2a9eN1kvfM0G{;9S7T3DH*h;S*Qc~s}<pxmlFJ<
zq(2nR!U8Go3kOZt=L+j#2T5TyH#f`vRV7>@CFy%jG{-nm35%`)BjVsk*P<W+v?K@K
zkKihCKq;H8?d1r=gxE|HQx)Pwg>f=f6LlkxSYfKo=DS#P)~{4_<!C4_mm_wGyq&b~
zelbZVIpMxes!s0#b#cnXmZ3;jci^L4IvOAuReQd}{{kX;LoznYo&;C~9%*_YeRy*_
zyxU0<_Ru-bEz_IFF6(RcZ9r0yD^`^ZZYj9NBnO0PG{1FRL!tFyNK{oyH&v$^b|<c?
zqaqN=w*i(qP?2*!j~WWbo%LmPk1QCb+Ro{vI5Spm_p$-Dg|~_!`KSMYex5q*Lw;`d
z0so_{0y`aSCHLZ_=iG8+efGK4^O%G!a*BZDYv5&UWZV)l)m7l~-lL)p+S7vJ3LUhP
z?=T0EB#xvG5$qJ#k{E$(TB5CH<mpY%3U$*LMxLK|217HP2QHJA$6C(2HO@}w*FX2}
zqxCcwt6iICufO8Q-<U)m-dOMq;SPQ^s2>sJJMZ>&xZ=<~k4=rgv3iBjJ?~EZ=uZ)_
z(>TGd!}$s>sr)^A4oL5TBZ2||u3!NGq<^?2XBST!Q|CX+hH5KzE6j+##8v*NSEnOx
z+w?#i961%JH!UB9cnvEf8K{I^SxoYsd5+g5?&F&*8WERd$du-$Nl~N*HDWOLQ&ZEd
zlQuSb2E&VWadd6bpH5gV&2Z<FOM>9bHG^);1~d)^Q5<b=gZORmYT-y!GdIfX=Y!&S
z)>);F5cF8yP~~&PYcHlD71Q-vD7DHc$4%W9iYiw)gjL1ecLqpWWw|A#SZgVb{?K)3
zwXbH5zu&UUt@~~bp_*<e>^ujpf{`<T7+bf%36jhr&^wyZ2QW^X4m;l@pJt2!$73Y}
ze2A1$(FA?4yp1PB(@=Y}niEh89gCC7l`7mv-f=<aFusYR%J(lCBMj_m*TDb5w4VxJ
z1^qS8u_A<HD99zQc_F9BBy$i6%g46KnXY)pXgyWL++zOpnIdeJm)wz$hr_bXO}}!@
z3#Ykr_GR871%V|p?|mMNq+O~KUPg}Jb5mtNP0-<SR%mX*8iB~|2izFOxSJ1#rE(BI
z9mX~drH#9#5vp-JmRkHv>F)Hbt-l-1G;O%#Vqq~pA@5wv?UPx2g<fI6e2TMgscli<
zbUfpKkXla`k=e|nn|iC6b#)TtDVQuk9rw;$n6JsOBPEQlxyDL5&y6+Vrb3c=3{3;N
z7hUuqMbEA!W^^96yqBmu)Vw>VfN$e9LKX0|M*ikzlOsos@}|N*L-eQJQu3gqKf|54
z)IxI}3!8MKn2zlog03rJaxZr<1hnzO#j2K2V#7^Z%_N|YPx`pDjtKpe?mER?6hV=Z
zsB`;vkJGihG(@e%XR`ZKxuZ~Hy7f)0sS-oVpTI{CF4;53=Ts~osy*1s$|tQAY_jgb
z>-M84!^1VhnD)x=UpI+Q5EafQSAG@VA95hHr*>v|CdgoWURpF?<P48H)sO7@?XN%K
z$Lzo2PMzSqDPj3aZv|nzdewbHD)818NMy_NP);l4J?2X!|9nJ!)_y#L(l(qp(YAEO
zdQn3Sr!hNx!7-A9cDq0J;WU9{UjX>or>;tuwR=8$K6`2ro~-+Z=|kKHpwp9XVdsCX
zz+-mRYITDH%2a#+0P~-UWbx6-)I`O_$<ogJPkqYJ0@<%{pgs#2zCwM(T!gWxrXEgI
zrC_|s9bR4<#^y!188);TFr)jzC`Ebs@{qY>cqGb#^-KyU98!IH`qLZ4I0$;7MY!rq
z+*Qs%JX7KllBNF@8Ff9pVdr=6%ptU_Se+Asd2CW;>~&`M^z1&UO#tm4B7kQTz0^U7
zeC^aLT@t&K4D`65R+B<{Dq0X}SBtK=3T08j?xjW?uFBIzoKjZr$w1736DUA`lIfqg
zrQ)ItKCj;0Hh$k>`X)Dx5M}(%LzDO<w(ufCC(K;AY`IhO8^c7gwk%WS^5m&m6dh%~
z-M4iawXzoCOtn(>_xppK)QBR_Dv!IAOe6iDBI=jwh%*Jsaop32`@;_UQ!h8m(W08^
z%N>eYbsdi6{C|mk$I)~2FM~!vosgP)(ZM-{(;K}xh*k=m$VZhuDKk&<Fsyr4W`|rm
zWYB|T&F({8#vq8ECXfw^%lm*E`?&|T{w4Wnh8jhDEyV#KwtpALGC)e(Ts7mWT~244
zR@bL~kVrpmo6lajpPG)8Hbh16QTA(2Cb5RB61vI9eGiEr`D_SIAek?`Xt@)jvIiBz
z!ZQ;+N%ZQmQ?IgGsPp3RY_<W5jYV8tYt@F5>HaWA8Zc%y)|&TSsu-Xm!g(K+2rLzp
zI%+Q%v8{kR*rW}>*GUY7=Grnx&W=imn%9A}2IFTH^?h+nUbamI#PM(UGd;Jur+MG`
z-+$=~OT^iRx_~|2IJ~OE*dQ)7ial$~3?T^g`v@QK6k%EW_#qchhc^2P?@U8NyaLw(
zR|MmM69WbNy?m;+I`&5%ASq7(YE3~i|Ca>rFA1W^!iuAEKgnnsu7YOKMOAZE`ls?$
z5#I*qqY^wEC!#dXCYx%60+e48Bdq(+sg_$vdHbOzI=>SY=M%}v1gZ#Q1k8lk%GpsW
z(xypEeiJL3z05+wi4E%e<^?Ap8kzx!JS#;?(T-<bXWr+i#!-V3oWt*hZYdF+Y|0hi
z_Z@!k8)81db%;GMTfQYW3ybZ$;5gR6>(cophEwx<vD#<^o7##iSG7EHx0f3#47vul
zeX@8*xUrQIWtSTD!;+PIp*t{malLgz#ID~Cgo6evbQ{W53x|9M4CJ7_B7(^fCtYE9
zm}%$aYy_>uPBbgUUyEJrqsoL|PLq1NS_{pUr*53w;KylQsrQ;7tSzE<y?==CJ3Pvm
zfr=)an9+XZPZzXebgl7T9XBvw7dC6|Q@MgQpB$1DRpNJAx(i@I{5g{Ot0?0VIe<u?
zl}ZnNC!<VUNvO@fzhWoGpdg?u;ZSJW5LpPvMdR#xK(lr(BW1?M?F``!A`B4*1heMt
z;w~buU>_gVM3tbjlG6NQ@7Puw&_n3Emfq24=~jIfc}V5h%0=_tesXj}kWPg6V$`<$
z?&CUKqRz(JD2syu!F;EqLnC5lcckc)TgagK>|>VLASp1O8s!37UACPQlEq~3728qc
z*_3R^wr*6Jmh#)QtF5i|?Se*6w;13()rUm%Z$n#N8RzY9c#&=szje}jHiuj+kFx17
zUVZ3g9m>8HRzJF#7+H!#13G16ZT0K3;7-pyV#CZHEnkQ(l?o90w6#BNA!fppRJ2Uh
zf!@JFl{s1Pz1<^nmG8>CTkkoA=`=yHn$*3<o_8WsbtbjO$_bet#Zh%o&vq8OU&a?=
zJH~$I;AOY%?@Jky;O5@IM*bO{LXipAWH_3_4@W_3J^1J?7E&xtK|C#sUDbI!YD^LK
zV=^E~xpMp+J)aXC={TRAnB6=K&k5o~=Pw0JBZRx!$=1OanToVIBY<z>!zb;^N7lt{
zj&<K4*N0XX`Ho^s)bf1GS_U0_>p8bm)5A%H1VEv{MP@#C6AMWw^-To3<E7TjxVZri
zM@>PBbwpPrduaa}Z<G7g$GE_9c#&@p1y%Wzn^AE?R9ka|ES4JXaIf0<;HHHC5<A7*
zv~`Gsoxw+NWQ7LatTM4TR&=s=aAq>LcQXBFyU_pksKCB3I$qB@m>Dw^1p9~*?;WG0
zzL1T5ql8<=tT{MvD(qxs`Yx0r{d%3r>WF@&pK<(g_nbS-q%^oJn2EW;O7*iOW-b8J
zUNnE?ZM)5nO?LP)W9h0ErMO&VdTp!}9K0WioG@9kx!q0hHXBkS$`#Ia?(!<p4C}!r
z92ZExdi9JcoL^=WHQ&E<OLs}VWvYT6gmy-}?NU?_brFRZAiXXuh7H)jwTjEm=%*mN
zD?I9weB28mO=UOz#dBiLb2zaS6uUVmuxLfwU`tSckiGc~^jqN*K*<eFI&|-cz)Ian
zBrvRC5fkh@MRpA}4||5RHv2gM^3n)wI*5cV2zs0l3iUV7;@po_L=D8r$$g>ml(Ppl
zSgTSv#)p3TM6os?lg4P_b-nibaO}s#MKqM#^%^0QMsMDSk&W9nNi22_j?4cZxC3Ds
zNTR^x!v<3m_20?&(ZS(=+yj&DpGQXgI5>wv{RDdRfD8#@`Beu8A8e#Z!Qf<}1f?E-
znXIiPO0B$M2i>Y*pe$_Dd{W%_jE5+QTx^HZPA4915?tBmr4|X<4ve{el;&G7s1%3@
z!u5e-^eF2?lUhBz1<i4ULXhj^k!g99hz|1E<WbCiM5&Xu{>EV&&hKEgtsmM@4+9GJ
zJejU-V;m)jfE8aibY{;$>_2Y8yZ4t%H)JK|pC2TJuvUYG(O4mJE#7HX`WDu$1(jh}
z*{Op86_Omq1RE?r{7aegkTC6s#r;?Q<nm=a2agowIR-9a%1Nl}fVke(pqRY*p>#B)
zFwMB<q^&mWeg%@TuSvM1+GiOKwKjGI%Se4nf?;>Ugk%ZvQp_lYPQ`i)H@W%>L8`j&
zwcUvE*eT)lreRmPKZSSvQ7cpWFnY&$w~txZeRkvRTby_fP(bzzom1P2Vcv#5qo+<q
zZiJ#X%BzJo3Q*T^Mp2CEtF9Zji*1%K`a3CpX`Rjb>t!P-re1yhvcs2Q3x5U75ReSu
z;P}5cT>fjp{x$xW_De;X{}k|_tzrKH{xPP2wc_6z#eN6=-Y)YOv<+OM{jGWCckqAq
zDEtKl06qc#1pohZEc`C#_l@hnBsC)Ze}Cd{+t|NL`Ms|EmlS<)8UntR->b~O3;4YP
z@RxvVa4G{9@K-(Hcj)gq&tFghqJKbt&wzfH@SiU9FFXLiLID8$&7uAd|4$?M@9>Iu
c{|5i3NmP`1172MK03Q4b0Q+ovnm?}o9|Ua)9RL6T

literal 0
HcmV?d00001

diff --git a/james_bond_data_cleansed.csv b/james_bond_data_cleansed.csv
new file mode 100644
index 0000000000..f57c20a4d8
--- /dev/null
+++ b/james_bond_data_cleansed.csv
@@ -0,0 +1,26 @@
+bond_actor,bond_kills,car_manufacturer,film_length,gross_income_usa,gross_income_world,imdb_rating,martinis_consumed,movie_budget,movie_title,release_date,rotten_tomatoes_rating,release_Year
+Sean Connery,4,Sunbeam,110,16067035.0,59567035.0,7.3,2,1000000.0,Dr. No,1962-06-01,7.7,1962
+Sean Connery,11,Bently,115,24800000.0,78900000.0,7.5,0,2000000.0,From Russia with Love,1963-08-01,8.0,1963
+Sean Connery,9,Aston Martin,110,51100000.0,124900000.0,7.8,1,3000000.0,Goldfinger,1964-05-01,8.4,1964
+Sean Connery,20,Aston Martin,130,63600000.0,141200000.0,7.0,0,9000000.0,Thunderball,1965-09-01,6.8,1965
+Sean Connery,21,Toyota,117,43100000.0,111600000.0,6.9,1,9500000.0,You Only Live Twice,1967-11-01,6.3,1967
+George Lazenby,5,Mercury,142,22800000.0,82000000.0,6.8,1,8000000.0,On Her Majesty's Secret Service,1969-07-01,6.7,1969
+Sean Connery,7,Ford,120,43800000.0,116000000.0,6.7,0,7200000.0,Diamonds Are Forever,1971-03-01,6.3,1971
+Roger Moore,8,AMC,121,35400000.0,161800000.0,6.8,0,7000000.0,Live and Let Die,1973-08-01,5.9,1973
+Roger Moore,1,AMC,125,21000000.0,97600000.0,6.7,0,7000000.0,The Man with the Golden Gun,1974-07-01,5.1,1974
+Roger Moore,31,Lotus,125,46800000.0,185400000.0,7.1,1,14000000.0,The Spy Who Loved Me,1977-04-01,6.8,1977
+Roger Moore,12,Lotus,126,70300000.0,210300000.0,6.2,1,31000000.0,Moonraker,1979-10-01,5.7,1979
+Roger Moore,18,Citroen,127,54800000.0,195300000.0,6.8,0,28000000.0,For Your Eyes Only,1981-06-01,6.3,1981
+Roger Moore,15,Bajaj,131,67900000.0,187500000.0,6.5,0,27500000.0,Octopussy,1983-03-01,5.3,1983
+Roger Moore,5,Rolls Royce,131,50327960.0,152627960.0,6.2,0,30000000.0,A View to a Kill,1985-10-01,4.7,1985
+Timothy Dalton,13,Rolls Royce,130,51185000.0,191200000.0,6.7,2,40000000.0,The Living Daylights,1987-05-01,6.3,1987
+Timothy Dalton,10,Aston Martin,133,34667015.0,156167015.0,6.5,1,42000000.0,License to Kill,1989-01-01,6.0,1989
+Pierce Brosnan,47,BMW,130,106429941.0,356429941.0,7.2,1,60000000.0,GoldenEye,1995-09-01,6.9,1995
+Pierce Brosnan,30,Aston Martin,119,125304276.0,339504276.0,6.4,1,110000000.0,Tomorrow Never Dies,1997-07-01,6.0,1997
+Pierce Brosnan,27,BMW,128,126930660.0,361730660.0,6.3,1,135000000.0,The World Is Not Enough,1999-06-01,5.7,1999
+Pierce Brosnan,31,Aston Martin,133,160942139.0,431942139.0,6.0,2,142000000.0,Die Another Day,2002-08-01,6.1,2002
+Daniel Craig,11,Aston Martin,144,167365000.0,596365000.0,7.9,3,102000000.0,Casino Royale,2006-02-01,7.8,2006
+Daniel Craig,16,Aston Martin,106,169368427.0,591692078.0,6.7,6,230000000.0,Quantum of Solace,2008-12-01,6.1,2008
+Daniel Craig,26,Aston Martin,143,304360277.0,1108561108.0,7.8,1,200000000.0,Skyfall,2012-11-01,8.2,2012
+Daniel Craig,30,Aston Martin,148,200074175.0,879620923.0,6.8,1,245000000.0,Spectre,2015-09-01,6.4,2015
+Daniel Craig,14,Aston Martin,163,160891007.0,759959662.0,7.3,1,275000000.0,No Time to Die,2021-11-01,7.3,2021