Skip to content

Instantly share code, notes, and snippets.

@audhiaprilliant

audhiaprilliant/monty_hall_problem.ipynb

Created April 25, 2022 15:42
Show Gist options

  • Select an option

    Learn more about clone URLs
  • Save audhiaprilliant/b0eee35179bdaa1f2af06a92f49f4131 to your computer and use it in GitHub Desktop.

Select an option

Learn more about clone URLs
Save audhiaprilliant/b0eee35179bdaa1f2af06a92f49f4131 to your computer and use it in GitHub Desktop.
Download ZIP
Simulation of Monty Hall Problem
Display the source blob
Display the rendered blob
Raw
monty_hall_problem.ipynb
{
"cells": [
{
"cell_type": "markdown",
"id": "powered-actress",
"metadata": {},
"source": [
"# Monty Hall Problem"
]
},
{
"cell_type": "markdown",
"id": "loved-apollo",
"metadata": {},
"source": [
"---"
]
},
{
"cell_type": "markdown",
"id": "persistent-savannah",
"metadata": {},
"source": [
"## Import packages"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "altered-jaguar",
"metadata": {},
"outputs": [],
"source": [
"# Data frame manipulation\n",
"import pandas as pd\n",
"\n",
"# Mathematical operations\n",
"import numpy as np\n",
"\n",
"# Data visualization\n",
"import plotnine\n",
"from plotnine import *\n",
"\n",
"# Randomization\n",
"import random"
]
},
{
"cell_type": "markdown",
"id": "reserved-composer",
"metadata": {},
"source": [
"## Empirical simulation"
]
},
{
"cell_type": "markdown",
"id": "eligible-collective",
"metadata": {},
"source": [
"### Scenario 1"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "interior-concert",
"metadata": {
"code_folding": [
24,
32,
40,
49
]
},
"outputs": [],
"source": [
"# Monty Hall Problem\n",
"def monty_hall(\n",
" num_iter: int,\n",
" switch: bool\n",
" ):\n",
" # Data object\n",
" obj = []\n",
" \n",
" for iteration in range(num_iter):\n",
" # Possibilities in doors\n",
" doors = ['Car', 'Zonk', 'Zonk']\n",
" # Random doors\n",
" random.shuffle(doors)\n",
" # Index of doors\n",
" l_doors = list(range(0, 3))\n",
" # Dictionary of doors\n",
" d_doors = dict(zip(l_doors, doors))\n",
" # Participant select the initial door\n",
" index_initial = random.choice(l_doors)\n",
" # Host select the zonk door\n",
" d_zonks = {k:v for k, v in d_doors.items() if (k != index_initial and v == 'Zonk')}\n",
" index_zonk = random.choice(list(d_zonks.keys()))\n",
" \n",
" # Strategy\n",
" if switch:\n",
" d_switch = {k:v for k, v in d_doors.items() if k not in [index_initial, index_zonk]}\n",
" switch_index, final_choice = list(d_switch.items())[0]\n",
" # Win-lose statistics\n",
" if final_choice == 'Car':\n",
" win, lose = 1, 0\n",
" else:\n",
" win, lose = 0, 1\n",
" else:\n",
" # Win-lose statistics\n",
" if d_doors[index_initial] == 'Car':\n",
" win, lose = 1, 0\n",
" else:\n",
" win, lose = 0, 1\n",
" \n",
" # Assign new values into list\n",
" try:\n",
" l_temp = [d for d in obj if d['iter'] == iteration][0]\n",
" obj.append(\n",
" {\n",
" 'iter': iteration + 1,\n",
" 'win': l_temp['win'] + win,\n",
" 'lose': l_temp['lose'] + lose\n",
" }\n",
" )\n",
" except:\n",
" obj.append(\n",
" {\n",
" 'iter': iteration + 1,\n",
" 'win': win,\n",
" 'lose': lose\n",
" }\n",
" )\n",
" \n",
" # Return list of object\n",
" return obj"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "latin-statistics",
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"[{'iter': 1, 'win': 1, 'lose': 0}]"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# One chance\n",
"monty_hall(\n",
" num_iter = 1,\n",
" switch = True\n",
")"
]
},
{
"cell_type": "markdown",
"id": "specialized-heritage",
"metadata": {},
"source": [
"#### Switch the door"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "capable-backup",
"metadata": {},
"outputs": [],
"source": [
"# Perform a empirical simulation\n",
"data_switch = monty_hall(\n",
" num_iter = 1000,\n",
" switch = True\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "sexual-bacteria",
"metadata": {},
"outputs": [],
"source": [
"# Create a data rame\n",
"df_switch = pd.DataFrame(\n",
" data = data_switch\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "altered-variance",
"metadata": {},
"outputs": [],
"source": [
"# Create a column of probability\n",
"df_switch['win_rate'] = (df_switch['win'] / df_switch['iter']).apply(\n",
" lambda x: round(x, 3)\n",
")\n",
"df_switch['lose_rate'] = (1 - df_switch['win_rate']).apply(\n",
" lambda x: round(x, 3)\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "graduate-medline",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>iter</th>\n",
" <th>win</th>\n",
" <th>lose</th>\n",
" <th>win_rate</th>\n",
" <th>lose_rate</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0.000</td>\n",
" <td>1.000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0.500</td>\n",
" <td>0.500</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.333</td>\n",
" <td>0.667</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4</td>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" <td>0.500</td>\n",
" <td>0.500</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5</td>\n",
" <td>3</td>\n",
" <td>2</td>\n",
" <td>0.600</td>\n",
" <td>0.400</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" iter win lose win_rate lose_rate\n",
"0 1 0 1 0.000 1.000\n",
"1 2 1 1 0.500 0.500\n",
"2 3 1 2 0.333 0.667\n",
"3 4 2 2 0.500 0.500\n",
"4 5 3 2 0.600 0.400"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Show data frame\n",
"df_switch.head()"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "intelligent-brief",
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 1000x480 with 1 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
},
{
"data": {
"text/plain": [
"<ggplot: (197526483098)>"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"plotnine.options.figure_size = (10, 4.8)\n",
"(\n",
" ggplot(\n",
" data = df_switch\n",
" )+\n",
" geom_line(\n",
" aes(x = 'iter',\n",
" y = 'win_rate',\n",
" group = 1),\n",
" size = 1)+\n",
" ylim(\n",
" [0, 1]\n",
" )+\n",
" scale_x_continuous(\n",
" breaks = range(0, len(df_switch) + 100, 100)\n",
" )+\n",
" labs(\n",
" title = 'Probability of winning the game (switch the door)'\n",
" )+\n",
" xlab(\n",
" xlab = 'Number of iteration'\n",
" )+\n",
" ylab(\n",
" ylab = 'Probability'\n",
" )+\n",
" theme_minimal()\n",
")"
]
},
{
"cell_type": "markdown",
"id": "nasty-martin",
"metadata": {},
"source": [
"#### Stick in the door"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "relative-synthesis",
"metadata": {},
"outputs": [],
"source": [
"# Perform a empirical simulation\n",
"data_stick = monty_hall(\n",
" num_iter = 1000,\n",
" switch = False\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "comparable-complex",
"metadata": {},
"outputs": [],
"source": [
"# Create a data rame\n",
"df_stick = pd.DataFrame(\n",
" data = data_stick\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "organized-russell",
"metadata": {},
"outputs": [],
"source": [
"# Create a column of probability\n",
"df_stick['win_rate'] = (df_stick['win'] / df_stick['iter']).apply(\n",
" lambda x: round(x, 3)\n",
")\n",
"df_stick['lose_rate'] = (1 - df_stick['win_rate']).apply(\n",
" lambda x: round(x, 3)\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "harmful-drive",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>iter</th>\n",
" <th>win</th>\n",
" <th>lose</th>\n",
" <th>win_rate</th>\n",
" <th>lose_rate</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>2</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4</td>\n",
" <td>0</td>\n",
" <td>4</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>5</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" iter win lose win_rate lose_rate\n",
"0 1 0 1 0.0 1.0\n",
"1 2 0 2 0.0 1.0\n",
"2 3 0 3 0.0 1.0\n",
"3 4 0 4 0.0 1.0\n",
"4 5 0 5 0.0 1.0"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Show data frame\n",
"df_stick.head()"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "honey-navigator",
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 1000x480 with 1 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
},
{
"data": {
"text/plain": [
"<ggplot: (197521661841)>"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"plotnine.options.figure_size = (10, 4.8)\n",
"(\n",
" ggplot(\n",
" data = df_stick\n",
" )+\n",
" geom_line(\n",
" aes(x = 'iter',\n",
" y = 'win_rate',\n",
" group = 1),\n",
" size = 1\n",
" )+\n",
" ylim(\n",
" [0, 1]\n",
" )+\n",
" scale_x_continuous(\n",
" breaks = range(0, len(df_stick) + 100, 100)\n",
" )+\n",
" labs(\n",
" title = 'Probability of winning the game (stick in the door)'\n",
" )+\n",
" xlab(\n",
" xlab = 'Number of iteration'\n",
" )+\n",
" ylab(\n",
" ylab = 'Probability'\n",
" )+\n",
" theme_minimal()\n",
")"
]
},
{
"cell_type": "markdown",
"id": "public-martial",
"metadata": {},
"source": [
"### Scenario 2"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "welcome-impression",
"metadata": {},
"outputs": [],
"source": [
"# Perform a empirical simulation\n",
"data_general = monty_hall(\n",
" num_iter = 1000,\n",
" switch = True\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "approximate-modification",
"metadata": {},
"outputs": [],
"source": [
"# Create a data rame\n",
"df_general = pd.DataFrame(\n",
" data = data_general\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "authorized-threshold",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>iter</th>\n",
" <th>win</th>\n",
" <th>lose</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4</td>\n",
" <td>3</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5</td>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" iter win lose\n",
"0 1 0 1\n",
"1 2 1 1\n",
"2 3 2 1\n",
"3 4 3 1\n",
"4 5 4 1"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Show data frame\n",
"df_general.head()"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "professional-young",
"metadata": {},
"outputs": [],
"source": [
"# Reshape the data\n",
"df_general = pd.melt(\n",
" frame = df_general,\n",
" id_vars = 'iter',\n",
" var_name = 'status',\n",
" value_name = 'value'\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "spanish-trader",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>iter</th>\n",
" <th>status</th>\n",
" <th>value</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>win</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>win</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
" <td>win</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4</td>\n",
" <td>win</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5</td>\n",
" <td>win</td>\n",
" <td>4</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" iter status value\n",
"0 1 win 0\n",
"1 2 win 1\n",
"2 3 win 2\n",
"3 4 win 3\n",
"4 5 win 4"
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Show data frame\n",
"df_general.head()"
]
},
{
"cell_type": "code",
"execution_count": 19,
"id": "weekly-competition",
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 1000x480 with 1 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
},
{
"data": {
"text/plain": [
"<ggplot: (197521662573)>"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"plotnine.options.figure_size = (10, 4.8)\n",
"(\n",
" ggplot(\n",
" data = df_general\n",
" )+\n",
" geom_line(\n",
" aes(x = 'iter',\n",
" y = 'value',\n",
" group = 'status',\n",
" color = 'status'),\n",
" size = 1\n",
" )+\n",
" scale_x_continuous(\n",
" breaks = range(0, len(df_general) + 100, 100)\n",
" )+\n",
" scale_color_manual(\n",
" values = ['#981220', '#80797c'],\n",
" labels = ['Stick', 'Switch']\n",
" )+\n",
" labs(\n",
" title = 'Probability of winning the game',\n",
" color = 'Strategy'\n",
" )+\n",
" xlab(\n",
" xlab = 'Number of iteration'\n",
" )+\n",
" ylab(\n",
" ylab = 'Number of chance'\n",
" )+\n",
" theme_minimal()+\n",
" theme(\n",
" legend_position = (0.225, 0.815),\n",
" legend_direction = 'horizontal'\n",
" )\n",
")"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"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": "3.8.3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment