s478991/Titanic_Machine_Learning_from_Disaster
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
019274795d
Titanic_Machine_Learning_fr.../analysis.ipynb

1366 lines
184 KiB
Plaintext
Raw Normal View History

Initian analysis
2023-02-16 13:32:30 +01:00
{
"cells": [
{
"cell_type": "markdown",
"id": "0ba6ee9e",
"metadata": {},
"source": [
Bad final predictions
2023-02-17 14:01:05 +01:00
"# Titanic Machine Learning from Disaster"
Initian analysis
2023-02-16 13:32:30 +01:00
]
},
{
"cell_type": "markdown",
"id": "ec6e69b1",
"metadata": {},
"source": [
Bad final predictions
2023-02-17 14:01:05 +01:00
"## Imports"
Initian analysis
2023-02-16 13:32:30 +01:00
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "ffcae455",
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"import pandas as pd\n",
"import matplotlib.pyplot as plt\n",
"import seaborn as sns\n",
"import plotly.express as px"
]
},
{
"cell_type": "markdown",
"id": "d1b19cf9",
"metadata": {},
"source": [
Bad final predictions
2023-02-17 14:01:05 +01:00
"## Data description"
Initian analysis
2023-02-16 13:32:30 +01:00
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "3174342e",
"metadata": {},
"outputs": [],
"source": [
Bad final predictions
2023-02-17 14:01:05 +01:00
"# Loading the data\n",
"df_train = pd.read_csv('train.csv')\n",
"df_test = pd.read_csv('test.csv')"
Initian analysis
2023-02-16 13:32:30 +01:00
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "4d561fad",
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"Index(['PassengerId', 'Survived', 'Pclass', 'Name', 'Sex', 'Age', 'SibSp',\n",
" 'Parch', 'Ticket', 'Fare', 'Cabin', 'Embarked'],\n",
" dtype='object')"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_train.columns"
]
},
{
"cell_type": "code",
"execution_count": 4,
Bad final predictions
2023-02-17 14:01:05 +01:00
"id": "b2bfda08",
Initian analysis
2023-02-16 13:32:30 +01:00
"metadata": {},
Bad final predictions
2023-02-17 14:01:05 +01:00
"outputs": [
{
"data": {
"text/plain": [
"Index(['PassengerId', 'Pclass', 'Name', 'Sex', 'Age', 'SibSp', 'Parch',\n",
" 'Ticket', 'Fare', 'Cabin', 'Embarked'],\n",
" dtype='object')"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_test.columns"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "7818fc15",
"metadata": {
"scrolled": true
},
Initian analysis
2023-02-16 13:32:30 +01:00
"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>PassengerId</th>\n",
" <th>Survived</th>\n",
" <th>Pclass</th>\n",
" <th>Age</th>\n",
" <th>SibSp</th>\n",
" <th>Parch</th>\n",
" <th>Fare</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>count</th>\n",
" <td>891.000000</td>\n",
" <td>891.000000</td>\n",
" <td>891.000000</td>\n",
" <td>714.000000</td>\n",
" <td>891.000000</td>\n",
" <td>891.000000</td>\n",
" <td>891.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>mean</th>\n",
" <td>446.000000</td>\n",
" <td>0.383838</td>\n",
" <td>2.308642</td>\n",
" <td>29.699118</td>\n",
" <td>0.523008</td>\n",
" <td>0.381594</td>\n",
" <td>32.204208</td>\n",
" </tr>\n",
" <tr>\n",
" <th>std</th>\n",
" <td>257.353842</td>\n",
" <td>0.486592</td>\n",
" <td>0.836071</td>\n",
" <td>14.526497</td>\n",
" <td>1.102743</td>\n",
" <td>0.806057</td>\n",
" <td>49.693429</td>\n",
" </tr>\n",
" <tr>\n",
" <th>min</th>\n",
" <td>1.000000</td>\n",
" <td>0.000000</td>\n",
" <td>1.000000</td>\n",
" <td>0.420000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25%</th>\n",
" <td>223.500000</td>\n",
" <td>0.000000</td>\n",
" <td>2.000000</td>\n",
" <td>20.125000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>7.910400</td>\n",
" </tr>\n",
" <tr>\n",
" <th>50%</th>\n",
" <td>446.000000</td>\n",
" <td>0.000000</td>\n",
" <td>3.000000</td>\n",
" <td>28.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>14.454200</td>\n",
" </tr>\n",
" <tr>\n",
" <th>75%</th>\n",
" <td>668.500000</td>\n",
" <td>1.000000</td>\n",
" <td>3.000000</td>\n",
" <td>38.000000</td>\n",
" <td>1.000000</td>\n",
" <td>0.000000</td>\n",
" <td>31.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>max</th>\n",
" <td>891.000000</td>\n",
" <td>1.000000</td>\n",
" <td>3.000000</td>\n",
" <td>80.000000</td>\n",
" <td>8.000000</td>\n",
" <td>6.000000</td>\n",
" <td>512.329200</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" PassengerId Survived Pclass Age SibSp \\\n",
"count 891.000000 891.000000 891.000000 714.000000 891.000000 \n",
"mean 446.000000 0.383838 2.308642 29.699118 0.523008 \n",
"std 257.353842 0.486592 0.836071 14.526497 1.102743 \n",
"min 1.000000 0.000000 1.000000 0.420000 0.000000 \n",
"25% 223.500000 0.000000 2.000000 20.125000 0.000000 \n",
"50% 446.000000 0.000000 3.000000 28.000000 0.000000 \n",
"75% 668.500000 1.000000 3.000000 38.000000 1.000000 \n",
"max 891.000000 1.000000 3.000000 80.000000 8.000000 \n",
"\n",
" Parch Fare \n",
"count 891.000000 891.000000 \n",
"mean 0.381594 32.204208 \n",
"std 0.806057 49.693429 \n",
"min 0.000000 0.000000 \n",
"25% 0.000000 7.910400 \n",
"50% 0.000000 14.454200 \n",
"75% 0.000000 31.000000 \n",
"max 6.000000 512.329200 "
]
},
Bad final predictions
2023-02-17 14:01:05 +01:00
"execution_count": 5,
Initian analysis
2023-02-16 13:32:30 +01:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_train.describe()"
]
},
{
Bad final predictions
2023-02-17 14:01:05 +01:00
"cell_type": "code",
"execution_count": 6,
"id": "9c83bffc",
"metadata": {
"scrolled": false
},
"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>PassengerId</th>\n",
" <th>Pclass</th>\n",
" <th>Age</th>\n",
" <th>SibSp</th>\n",
" <th>Parch</th>\n",
" <th>Fare</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>count</th>\n",
" <td>418.000000</td>\n",
" <td>418.000000</td>\n",
" <td>332.000000</td>\n",
" <td>418.000000</td>\n",
" <td>418.000000</td>\n",
" <td>417.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>mean</th>\n",
" <td>1100.500000</td>\n",
" <td>2.265550</td>\n",
" <td>30.272590</td>\n",
" <td>0.447368</td>\n",
" <td>0.392344</td>\n",
" <td>35.627188</td>\n",
" </tr>\n",
" <tr>\n",
" <th>std</th>\n",
" <td>120.810458</td>\n",
" <td>0.841838</td>\n",
" <td>14.181209</td>\n",
" <td>0.896760</td>\n",
" <td>0.981429</td>\n",
" <td>55.907576</td>\n",
" </tr>\n",
" <tr>\n",
" <th>min</th>\n",
" <td>892.000000</td>\n",
" <td>1.000000</td>\n",
" <td>0.170000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25%</th>\n",
" <td>996.250000</td>\n",
" <td>1.000000</td>\n",
" <td>21.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>7.895800</td>\n",
" </tr>\n",
" <tr>\n",
" <th>50%</th>\n",
" <td>1100.500000</td>\n",
" <td>3.000000</td>\n",
" <td>27.000000</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" <td>14.454200</td>\n",
" </tr>\n",
" <tr>\n",
" <th>75%</th>\n",
" <td>1204.750000</td>\n",
" <td>3.000000</td>\n",
" <td>39.000000</td>\n",
" <td>1.000000</td>\n",
" <td>0.000000</td>\n",
" <td>31.500000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>max</th>\n",
" <td>1309.000000</td>\n",
" <td>3.000000</td>\n",
" <td>76.000000</td>\n",
" <td>8.000000</td>\n",
" <td>9.000000</td>\n",
" <td>512.329200</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" PassengerId Pclass Age SibSp Parch Fare\n",
"count 418.000000 418.000000 332.000000 418.000000 418.000000 417.000000\n",
"mean 1100.500000 2.265550 30.272590 0.447368 0.392344 35.627188\n",
"std 120.810458 0.841838 14.181209 0.896760 0.981429 55.907576\n",
"min 892.000000 1.000000 0.170000 0.000000 0.000000 0.000000\n",
"25% 996.250000 1.000000 21.000000 0.000000 0.000000 7.895800\n",
"50% 1100.500000 3.000000 27.000000 0.000000 0.000000 14.454200\n",
"75% 1204.750000 3.000000 39.000000 1.000000 0.000000 31.500000\n",
"max 1309.000000 3.000000 76.000000 8.000000 9.000000 512.329200"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
Initian analysis
2023-02-16 13:32:30 +01:00
"source": [
Bad final predictions
2023-02-17 14:01:05 +01:00
"df_test.describe()"
Initian analysis
2023-02-16 13:32:30 +01:00
]
},
{
"cell_type": "code",
Bad final predictions
2023-02-17 14:01:05 +01:00
"execution_count": 7,
"id": "0b345650",
Initian analysis
2023-02-16 13:32:30 +01:00
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
Bad final predictions
2023-02-17 14:01:05 +01:00
"PassengerId 0\n",
"Survived 0\n",
"Pclass 0\n",
"Name 0\n",
"Sex 0\n",
"Age 177\n",
"SibSp 0\n",
"Parch 0\n",
"Ticket 0\n",
"Fare 0\n",
"Cabin 687\n",
"Embarked 2\n",
"dtype: int64"
Initian analysis
2023-02-16 13:32:30 +01:00
]
},
Bad final predictions
2023-02-17 14:01:05 +01:00
"execution_count": 7,
Initian analysis
2023-02-16 13:32:30 +01:00
"metadata": {},
"output_type": "execute_result"
Bad final predictions
2023-02-17 14:01:05 +01:00
}
],
"source": [
"df_train.isna().sum()"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "af40052a",
"metadata": {},
"outputs": [
Initian analysis
2023-02-16 13:32:30 +01:00
{
"data": {
"text/plain": [
Bad final predictions
2023-02-17 14:01:05 +01:00
"PassengerId 0\n",
"Pclass 0\n",
"Name 0\n",
"Sex 0\n",
"Age 86\n",
"SibSp 0\n",
"Parch 0\n",
"Ticket 0\n",
"Fare 1\n",
"Cabin 327\n",
"Embarked 0\n",
"dtype: int64"
Initian analysis
2023-02-16 13:32:30 +01:00
]
},
Bad final predictions
2023-02-17 14:01:05 +01:00
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
Initian analysis
2023-02-16 13:32:30 +01:00
}
],
"source": [
Bad final predictions
2023-02-17 14:01:05 +01:00
"df_test.isna().sum()"
Initian analysis
2023-02-16 13:32:30 +01:00
]
},
{
"cell_type": "code",
Bad final predictions
2023-02-17 14:01:05 +01:00
"execution_count": 9,
"id": "8cec8cda",
Initian analysis
2023-02-16 13:32:30 +01:00
"metadata": {},
"outputs": [],
"source": [
Bad final predictions
2023-02-17 14:01:05 +01:00
"df_test['Fare'].fillna(df_test['Fare'].mean(), inplace=True)"
Initian analysis
2023-02-16 13:32:30 +01:00
]
},
{
"cell_type": "code",
Bad final predictions
2023-02-17 14:01:05 +01:00
"execution_count": 10,
"id": "6f612c59",
Initian analysis
2023-02-16 13:32:30 +01:00
"metadata": {},
"outputs": [],
"source": [
Bad final predictions
2023-02-17 14:01:05 +01:00
"df_test['Cabin'].fillna('Other', inplace=True)"
Initian analysis
2023-02-16 13:32:30 +01:00
]
},
{
Bad final predictions
2023-02-17 14:01:05 +01:00
"cell_type": "markdown",
"id": "07234316",
Initian analysis
2023-02-16 13:32:30 +01:00
"metadata": {},
"source": [
Bad final predictions
2023-02-17 14:01:05 +01:00
"## Preexploratory Data Analysis"
Initian analysis
2023-02-16 13:32:30 +01:00
]
},
{
"cell_type": "code",
Bad final predictions
2023-02-17 14:01:05 +01:00
"execution_count": 11,
"id": "2facd3d5",
Initian analysis
2023-02-16 13:32:30 +01:00
"metadata": {},
Bad final predictions
2023-02-17 14:01:05 +01:00
"outputs": [
{
"data": {
"text/plain": [
"(342, 549)"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
Initian analysis
2023-02-16 13:32:30 +01:00
"source": [
Bad final predictions
2023-02-17 14:01:05 +01:00
"len(df_train[df_train['Survived']==1]), len(df_train[df_train['Survived']==0])"
Initian analysis
2023-02-16 13:32:30 +01:00
]
},
{
"cell_type": "code",
Bad final predictions
2023-02-17 14:01:05 +01:00
"execution_count": 12,
"id": "1472e369",
"metadata": {},
Initian analysis
2023-02-16 13:32:30 +01:00
"outputs": [
{
"data": {
"text/plain": [
Bad final predictions
2023-02-17 14:01:05 +01:00
"<seaborn.axisgrid.FacetGrid at 0x1e194179a00>"
Initian analysis
2023-02-16 13:32:30 +01:00
]
},
Bad final predictions
2023-02-17 14:01:05 +01:00
"execution_count": 12,
Initian analysis
2023-02-16 13:32:30 +01:00
"metadata": {},
"output_type": "execute_result"
Bad final predictions
2023-02-17 14:01:05 +01:00
},
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAWAAAAFgCAYAAACFYaNMAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjQuMywgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/MnkTPAAAACXBIWXMAAAsTAAALEwEAmpwYAABHU0lEQVR4nO3deXhU5dnH8e89M5nJvhAS9i3sBAQFEXEHRKxWrbVqa2ttq5aq7avVVruAW0VwAcGlSK2tti61FZeCiIC7EBZlh7AjBIKQANkz6/P+kWARAtlm5sxyf64rF8nMyTm3TvLLM895FjHGoJRSKvxsVheglFLxSgNYKaUsogGslFIW0QBWSimLaAArpZRFHFYXEArjxo0z7777rtVlKKXUEdLQgzHZAi4pKbG6BKWUalRMBrBSSkUDDWCllLKIBrBSSllEA1gppSyiAayUUhbRAFZKKYtoACullEU0gJVSyiIawEopZRENYKWUsogGsFJKWUQDWCmlLBKTq6EppYLr5Zdf5s03ZgNN20MyIcHJHydMpH///qEtLMppACulTqq0tJS//+1vdEysoUuKr0nfs6okkVmznmXatCdCW1yU0wBWSp3Uq6++is/n5db8CtolB5r0Pe/u9vPyylWsXr2awYMHh7jC6KV9wEqpE9q/fz9vvfkmZ7WrbXL4AozqWEumC/763F8wpmndFvFIA1gpdUIzZ/4ZE/DynR41zfo+px2u6F7JmrXr+PDDD0NTXAzQAFZKNWj16tW8//4HXNKlmrZJTW/9HnF+Rzfd0gI88/RT1NbWhqDC6KcBrJQ6jsfjYdrUx8lOgku6Na/1e4RN4Ie9KzhQUsrf//734BYYIzSAlVLHeeGFF9j55S5u6FOOy97y8/TN9HF+x1pe+9e/WL9+ffAKjBEawEqpbygsLOSVl1/mnA61DM72tvp83+9VTVaiYfLDk3C73UGoMHZoACulvlZZWckD999Hpsvwg17VQTlnksPws77l7C7aw5NPPhmUc8YKHQccRzweD2+++eY3bojk5eVx9tlnW1iVihTGGB599BH27dvH708tIyUheMPHBrbxcknXGubMmcOQIUMYM2ZM0M4dzSwNYBF5HrgU2G+MGdjA89cBd9d/WQn8whizOowlxpTFixfzzDPPfOMxR0IC8955h4SEBIuqUpHijTfe4KOPPuaanlX0yWzajLfmuCqvmi3lCTz26CP07t2bbt26Bf0a0cbqLoi/A+NO8vwO4DxjzCnAg8CscBQVqwoLC8Fmp+K066kYdgM1eefh83rZvn271aUpi33xxRc89dRTnNrWw8VdQzNkzG6DW/IrcOLh97+7h/Ly8pBcJ5pYGsDGmI+Bgyd5frEx5lD9lwVA57AUFqM2biwkkNQG7A4QG/6UHKA+mFXc2r17N/dOmECHZB/jB1Rik9Bdq40rwP8NLOOrfcXcO3EiPl/wW9rRxOoWcHP8DJh3oidF5GYRWSEiKw4cOBDGsqKD1+tlw8YN+FJzvn7MuNIQZzJr1661sDJlpbKyMn53z93greKOQWUkOUI/bbh3ho+f9q1g5apVTJs2La6nKkdFAIvIBdQF8N0nOsYYM8sYM8wYMywnJ+dEh8WtwsJCvB4P/rT2/3tQBE9KO75YuTKufwniVU1NDffc/Vu+Kt7LrwaWkduC2W4tdXYHD9/uVs3cuXPjepJGxAewiJwCPAdcbowptbqeaLVy5UoA/Kntv/G4P709B0tL2bNnjxVlKYv4fD7uu/deCjdt4hf5FfQNwU23xlyVV8M5HWp54YUXeOutt8J+/UgQ0QEsIl2B2cCPjDGbra4nmhUULCWQ0haTkPiNx33pnQBYunSpFWUpC/j9fiZPnszSZcu4oU8lw3I8ltQhAj/tW8WpbT088cQ0Fi1aZEkdVrI0gEXkFWAJ0FdEikTkZyIyXkTG1x8yEcgGnhGRVSKywrJio1h5eTkbN27Am3H8PUyTmA5JGRQUFFhQmQq3QCDA1KlTWbhwId/Lq+KCTtbOTDsyMqJvpo+HHnqITz75xNJ6ws3qURDfN8Z0MMYkGGM6G2P+aoyZaYyZWf/8jcaYLGPMkPqPYVbWG62WLFmCMQZfRpcGn/ekd+aLlSupqqoKc2UqnIwxzJgxg7lz53J592q+3T0yVihz2eGOQWXkpXm5/7774qoxENFdECo4PvroI3ClEkhp2+Dzvqzu+H0+lixZEubKVLgYY3j66ad58803ubhrDVc2c33fUEtywJ2nlNE5xcuECX+Mmy4xDeAYV1lZybJly/Fkdq3rdGuAPzUXcSbzwQcfhLk6FQ5HWr7/+c9/GNu5hmt7Vp/oR8FSKQmG3ww+TMdED3/8w+/joiWsARzjPv74Y3w+L942eSc+SAR3Vg8KCgp0dlKMMcYwffp03njjDcZ1qeG63pEZvkekJRjuHnKYTsleJvzxDyxevNjqkkJKAzjGvffee5CUQSDl5GOjvdk98fv9un1MDAkEAjz++ONfdzt8v1dkh+8RqQmGuwcfpnOyh4kTJsT0jTkN4BhWXFzMqtWrcbfpecLuhyMCydmY5CzeeeedMFWnQsnv9zNlyhTmzJnDt7tVR2y3w4mkJBh+O7iM7qke7r33Xt5//32rSwoJDeAYNm/ePDAGb3avxg8WwZ3dm8LCQl2cJ8r5fHVDuubPn8+VPaq5Kq8mqsL3iCN9wr3SPfzpwQfr3s3FGA3gGOXz+Zg79x18GZ0xrtSmfU92L7DZmDt3boirU6Hi9Xp54IEHeP/99/leXhVX9IjO8D0iyQG/GVxGv0wvDz88KebeoWkAx6iCggJKS0vw5vRp8veYhES8md2Y9+67uottFPJ46t6uf/zxx/ygV1XEjPNtLZcdfn1KGflZXh555JGYmrasARyj3njzTXCl4Mvs2qzv8+b2p7qqSoekRRm3282ECX9k8eLFXN+nknEhWtPXKk473D6onMHZHqZNm8bs2bOtLikoNIBjUFFREZ+vWIE7uw9I815if2o7THIWs994I0TVqWDzeOpGCyxduoyf9K1kTOfY3PjSaYf/G1TB0BwPM2bMiIkQ1gCOQW+99RaIDW9O3+Z/swjutn3ZsnkzGzduDH5xKqg8Hg8TJ05g6bK68LV6bYdQc9jg1vwKhratC+E3oryhoAEcY2pra5n7zjt4s7phnMktOoe3bW/E4Yz6H+5Y5/P5uO++eykoWBoX4XuEwwa3Dqzg1LYepk+fzn//+1+rS2oxDeAYs2jRIqqrqvDm9m/5SewJuNv05P33P+Dw4cNBq00FTyAQYPLkySxevITr+8RP+B7hsMEvB1YwONvL1KmPR+04YQ3gGPPGm29ikrPwp7Zr1Xm8uf3w+by8++67QapMBYsxhieffJKFCxdyVV51zPb5NsZhg9sGltMnw8ekhx6KygV8NIBjSGFhIVu3bMGd06/RmW+NCSRl4U9rzxtvvkkgEL6talTjXnrpJd544w0u7lLDt7tF1qpm4eaywx2nlNMp2cvECX+Mug1mNYBjyNy5cxF7At42PYNyPk9OX77at49Vq1YF5Xyq9T766COee+45zmzn5tooWdsh1JIdhrsGHybN7uUPv7uHaNqUVwM4RtTU1LBg4UI8md3A4QzKOX1Z3RCHS2fGRYhNmzYx6aE/0SvDz8/6VWr4HiXDabhj0GGqKg7z+9/9jpqa6HhnoAEcIz755BNqa2qaNfOtUTYH7jZ5fPTRx1RWVgbvvKrZKioq+OMffk+q3cv/DSrDabe6osjTJdXPLQPK2bptK1OnTrW6nCbRAI4RCxcuhMS0Vt98O5Y3uyc+n5dPP/00qOdVTWeM4bHHHuVgaSm/zD9MhtNYXVLEGtLWy+XdqlmwYEHd70SE0wCOAYcPH2bFihW4M7u3+ubbsQIpOZCYzsI43LE2UsybN4+PPvqY7+ZVkZfut7qciHd59xp6Z/iZ+vhjFBcXW13OSWkAx4CCggICgQC+Nj2Cf3IR3JndWPnFF7pppwUOHTrEU0/OoH+Wj2/F2PoOoWK3wfgB5RhfLU9Mm2Z1OSelARwDlixZgjiTCSRnh+T8/swu+P1+VqxYEZLzqxN
"text/plain": [
"<Figure size 360x360 with 1 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
Initian analysis
2023-02-16 13:32:30 +01:00
}
],
"source": [
Bad final predictions
2023-02-17 14:01:05 +01:00
"sns.catplot(x='Sex', y='Survived', data=df_train, kind='violin')"
Initian analysis
2023-02-16 13:32:30 +01:00
]
},
{
"cell_type": "code",
Bad final predictions
2023-02-17 14:01:05 +01:00
"execution_count": 13,
"id": "6b33f748",
Initian analysis
2023-02-16 13:32:30 +01:00
"metadata": {
Bad final predictions
2023-02-17 14:01:05 +01:00
"scrolled": true
Initian analysis
2023-02-16 13:32:30 +01:00
},
"outputs": [
{
"data": {
"text/plain": [
Bad final predictions
2023-02-17 14:01:05 +01:00
"<AxesSubplot:xlabel='Sex', ylabel='Survived'>"
Initian analysis
2023-02-16 13:32:30 +01:00
]
},
Bad final predictions
2023-02-17 14:01:05 +01:00
"execution_count": 13,
Initian analysis
2023-02-16 13:32:30 +01:00
"metadata": {},
"output_type": "execute_result"
Bad final predictions
2023-02-17 14:01:05 +01:00
},
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 432x288 with 1 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
Initian analysis
2023-02-16 13:32:30 +01:00
}
],
"source": [
Bad final predictions
2023-02-17 14:01:05 +01:00
"sns.barplot(x='Sex', y='Survived', data=df_train)"
Initian analysis
2023-02-16 13:32:30 +01:00
]
},
{
"cell_type": "code",
Bad final predictions
2023-02-17 14:01:05 +01:00
"execution_count": 14,
"id": "99710899",
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"<AxesSubplot:xlabel='Age', ylabel='Count'>"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 432x288 with 1 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"sns.histplot(x='Age', hue='Survived', data=df_train, bins=20)"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "58c6b951",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<AxesSubplot:xlabel='Pclass', ylabel='Count'>"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 432x288 with 1 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"sns.histplot(x='Pclass', hue='Survived', data=df_train, bins=20)"
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "538c8c4f",
"metadata": {},
"outputs": [],
"source": [
"# sns.pairplot(data=df_train, hue='Survived')"
]
},
{
"cell_type": "markdown",
"id": "06684f27",
"metadata": {},
"source": [
"## Data Cleaning"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "095ae1ae",
"metadata": {},
"outputs": [],
"source": [
"df_train = pd.get_dummies(data=df_train, columns=['Sex', 'Embarked'])\n",
"df_test = pd.get_dummies(data=df_test, columns=['Sex', 'Embarked'])"
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "50c17ca4",
"metadata": {},
"outputs": [],
"source": [
"# df_train.drop(['Sex_male', 'Name', 'Ticket', 'PassengerId'], axis=1, inplace=True)\n",
"df_train.drop('Sex_male', axis=1, inplace=True)\n",
"df_test.drop('Sex_male', axis=1, inplace=True)"
]
},
{
"cell_type": "code",
"execution_count": 19,
"id": "0fdf3229",
"metadata": {},
"outputs": [],
"source": [
"df_train['Age'] = df_train['Age'].fillna(df_train['Age'].mean())\n",
"df_test['Age'] = df_test['Age'].fillna(df_train['Age'].mean())"
]
},
{
"cell_type": "code",
"execution_count": 20,
"id": "b1949435",
"metadata": {},
"outputs": [],
"source": [
"df_train['Cabin'] = df_train['Cabin'].fillna('Other')"
]
},
{
"cell_type": "code",
"execution_count": 21,
"id": "8a75aa3b",
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"array(['Other', 'C85', 'C123', 'E46', 'G6', 'C103', 'D56', 'A6',\n",
" 'C23 C25 C27', 'B78', 'D33', 'B30', 'C52', 'B28', 'C83', 'F33',\n",
" 'F G73', 'E31', 'A5', 'D10 D12', 'D26', 'C110', 'B58 B60', 'E101',\n",
" 'F E69', 'D47', 'B86', 'F2', 'C2', 'E33', 'B19', 'A7', 'C49', 'F4',\n",
" 'A32', 'B4', 'B80', 'A31', 'D36', 'D15', 'C93', 'C78', 'D35',\n",
" 'C87', 'B77', 'E67', 'B94', 'C125', 'C99', 'C118', 'D7', 'A19',\n",
" 'B49', 'D', 'C22 C26', 'C106', 'C65', 'E36', 'C54',\n",
" 'B57 B59 B63 B66', 'C7', 'E34', 'C32', 'B18', 'C124', 'C91', 'E40',\n",
" 'T', 'C128', 'D37', 'B35', 'E50', 'C82', 'B96 B98', 'E10', 'E44',\n",
" 'A34', 'C104', 'C111', 'C92', 'E38', 'D21', 'E12', 'E63', 'A14',\n",
" 'B37', 'C30', 'D20', 'B79', 'E25', 'D46', 'B73', 'C95', 'B38',\n",
" 'B39', 'B22', 'C86', 'C70', 'A16', 'C101', 'C68', 'A10', 'E68',\n",
" 'B41', 'A20', 'D19', 'D50', 'D9', 'A23', 'B50', 'A26', 'D48',\n",
" 'E58', 'C126', 'B71', 'B51 B53 B55', 'D49', 'B5', 'B20', 'F G63',\n",
" 'C62 C64', 'E24', 'C90', 'C45', 'E8', 'B101', 'D45', 'C46', 'D30',\n",
" 'E121', 'D11', 'E77', 'F38', 'B3', 'D6', 'B82 B84', 'D17', 'A36',\n",
" 'B102', 'B69', 'E49', 'C47', 'D28', 'E17', 'A24', 'C50', 'B42',\n",
" 'C148'], dtype=object)"
]
},
"execution_count": 21,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_train['Cabin'].unique()"
]
},
{
"cell_type": "code",
"execution_count": 22,
"id": "875d207c",
"metadata": {
"scrolled": false
},
"outputs": [
{
"data": {
"text/plain": [
"Other 687\n",
"C23 C25 C27 4\n",
"G6 4\n",
"B96 B98 4\n",
"C22 C26 3\n",
" ... \n",
"E34 1\n",
"C7 1\n",
"C54 1\n",
"E36 1\n",
"C148 1\n",
"Name: Cabin, Length: 148, dtype: int64"
]
},
"execution_count": 22,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_train['Cabin'].value_counts()"
]
},
{
"cell_type": "code",
"execution_count": 23,
"id": "56c071c5",
"metadata": {},
"outputs": [],
"source": [
"# df_train['Cabin'].str.extract('(\\d+)')"
]
},
{
"cell_type": "code",
"execution_count": 24,
"id": "d0163d74",
"metadata": {},
"outputs": [],
"source": [
"df_train['Cabin symbol'] = df_train['Cabin'].str.extract('(\\w)')\n",
"df_test['Cabin symbol'] = df_test['Cabin'].str.extract('(\\w)')"
]
},
{
"cell_type": "code",
"execution_count": 25,
"id": "b0f96907",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"O 327\n",
"C 35\n",
"B 18\n",
"D 13\n",
"E 9\n",
"F 8\n",
"A 7\n",
"G 1\n",
"dtype: int64"
]
},
"execution_count": 25,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_test['Cabin'].str.extract('(\\w)').value_counts()"
]
},
{
"cell_type": "code",
"execution_count": 26,
"id": "48944d81",
"metadata": {},
"outputs": [],
"source": [
"symbol_hist = df_train[df_train['Cabin symbol'] != 'O'][['Cabin symbol', 'Survived']]"
]
},
{
"cell_type": "code",
"execution_count": 27,
"id": "7fde7d54",
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"<AxesSubplot:xlabel='Cabin symbol', ylabel='Count'>"
]
},
"execution_count": 27,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 432x288 with 1 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"sns.histplot(x='Cabin symbol', hue='Survived', data=symbol_hist, bins=20)"
]
},
{
"cell_type": "code",
"execution_count": 28,
"id": "19d57354",
"metadata": {},
"outputs": [],
"source": [
"# Describe the 'Cabin' with number of people in it\n",
"counts_train = df_train['Cabin'].value_counts().copy(deep=True)\n",
"counts_test = df_test['Cabin'].value_counts().copy(deep=True)\n",
"\n",
"# Changing n-people cabin to 'description'\n",
"def num_peopl_in_cabin(df, n, description, counts):\n",
" df['Cabin'][df['Cabin'].isin(counts[counts==n].index)] = description"
]
},
{
"cell_type": "code",
"execution_count": 29,
"id": "fdcbf0a5",
"metadata": {
"scrolled": true
},
"outputs": [
{
"name": "stderr",
Initian analysis
2023-02-16 13:32:30 +01:00
"output_type": "stream",
"text": [
Bad final predictions
2023-02-17 14:01:05 +01:00
"C:\\Users\\Maciej\\AppData\\Local\\Temp/ipykernel_16012/2825624458.py:7: SettingWithCopyWarning: \n",
Initian analysis
2023-02-16 13:32:30 +01:00
"A value is trying to be set on a copy of a slice from a DataFrame\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
Bad final predictions
2023-02-17 14:01:05 +01:00
" df['Cabin'][df['Cabin'].isin(counts[counts==n].index)] = description\n"
Initian analysis
2023-02-16 13:32:30 +01:00
]
}
],
"source": [
Bad final predictions
2023-02-17 14:01:05 +01:00
"\n",
"num_peopl_in_cabin(df_train, 1, 'Alone', counts_train)\n",
"num_peopl_in_cabin(df_train, 2, 'Double room', counts_train)\n",
"num_peopl_in_cabin(df_train, 3, 'Three person room', counts_train)\n",
"num_peopl_in_cabin(df_train, 4, 'Four person room', counts_train)\n",
"\n",
"num_peopl_in_cabin(df_test, 1, 'Alone', counts_test)\n",
"num_peopl_in_cabin(df_test, 2, 'Double room', counts_test)\n",
"num_peopl_in_cabin(df_test, 3, 'Three person room', counts_test)\n",
"\n",
"\n",
"# df_train['Cabin'][df_train['Cabin'].isin(counts[counts>4].index)] = 'Other'\n",
"\n",
"# df_train['Cabin'][df_train['Cabin'].isin(counts[counts==1].index)] = 'Alone'\n",
"# df_train['Cabin'][df_train['Cabin'].isin(counts[counts==2].index)] = 'Double room'\n",
"# df_train['Cabin'][df_train['Cabin'].isin(counts[counts==3].index)] = 'Three person room'\n",
"# df_train['Cabin'][df_train['Cabin'].isin(counts[counts==4].index)] = 'Four person room'\n",
"# df_train['Cabin'][df_train['Cabin'].isin(counts[counts>4].index)] = 'Other'"
Initian analysis
2023-02-16 13:32:30 +01:00
]
},
{
"cell_type": "code",
Bad final predictions
2023-02-17 14:01:05 +01:00
"execution_count": 30,
Initian analysis
2023-02-16 13:32:30 +01:00
"id": "6d73e794",
Bad final predictions
2023-02-17 14:01:05 +01:00
"metadata": {
"scrolled": true
},
Initian analysis
2023-02-16 13:32:30 +01:00
"outputs": [
{
"data": {
"text/plain": [
"Other 687\n",
"Alone 101\n",
"Double room 76\n",
"Three person room 15\n",
"Four person room 12\n",
"Name: Cabin, dtype: int64"
]
},
Bad final predictions
2023-02-17 14:01:05 +01:00
"execution_count": 30,
Initian analysis
2023-02-16 13:32:30 +01:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_train['Cabin'].value_counts()"
]
},
{
"cell_type": "code",
Bad final predictions
2023-02-17 14:01:05 +01:00
"execution_count": 31,
Initian analysis
2023-02-16 13:32:30 +01:00
"id": "ae86ac06",
"metadata": {},
"outputs": [],
"source": [
Bad final predictions
2023-02-17 14:01:05 +01:00
"df_train = pd.get_dummies(data=df_train, columns=['Cabin'])\n",
"df_test = pd.get_dummies(data=df_test, columns=['Cabin', 'Pclass', 'Cabin symbol'])"
]
},
{
"cell_type": "code",
"execution_count": 32,
"id": "702cf4b1",
"metadata": {},
"outputs": [],
"source": [
"df_train = pd.get_dummies(data=df_train, columns=['Pclass'])"
]
},
{
"cell_type": "code",
"execution_count": 33,
"id": "2c5e0c67",
"metadata": {},
"outputs": [],
"source": [
"df_train = pd.get_dummies(data=df_train, columns=['Cabin symbol'])"
]
},
{
"cell_type": "code",
"execution_count": 34,
"id": "76796bf2",
"metadata": {},
"outputs": [],
"source": [
"df_train = df_train.drop('Cabin symbol_O', axis=1)\n",
"df_test = df_test.drop('Cabin symbol_O', axis=1)"
]
},
{
"cell_type": "code",
"execution_count": 35,
"id": "4be06019",
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"Index(['PassengerId', 'Name', 'Age', 'SibSp', 'Parch', 'Ticket', 'Fare',\n",
" 'Sex_female', 'Embarked_C', 'Embarked_Q', 'Embarked_S', 'Cabin_Alone',\n",
" 'Cabin_Double room', 'Cabin_Other', 'Cabin_Three person room',\n",
" 'Pclass_1', 'Pclass_2', 'Pclass_3', 'Cabin symbol_A', 'Cabin symbol_B',\n",
" 'Cabin symbol_C', 'Cabin symbol_D', 'Cabin symbol_E', 'Cabin symbol_F',\n",
" 'Cabin symbol_G'],\n",
" dtype='object')"
]
},
"execution_count": 35,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_test.columns"
]
},
{
"cell_type": "code",
"execution_count": 36,
"id": "c9e20ea5",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Index(['PassengerId', 'Name', 'Age', 'SibSp', 'Parch', 'Ticket', 'Fare',\n",
" 'Sex_female', 'Embarked_C', 'Embarked_Q', 'Embarked_S', 'Cabin_Alone',\n",
" 'Cabin_Double room', 'Cabin_Other', 'Cabin_Three person room',\n",
" 'Pclass_1', 'Pclass_2', 'Pclass_3', 'Cabin symbol_A', 'Cabin symbol_B',\n",
" 'Cabin symbol_C', 'Cabin symbol_D', 'Cabin symbol_E', 'Cabin symbol_F',\n",
" 'Cabin symbol_G'],\n",
" dtype='object')"
]
},
"execution_count": 36,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_test.columns[df_test.columns.isin(df_train.columns)]"
]
},
{
"cell_type": "code",
"execution_count": 37,
"id": "a6a53564",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Index(['PassengerId', 'Survived', 'Name', 'Age', 'SibSp', 'Parch', 'Ticket',\n",
" 'Fare', 'Sex_female', 'Embarked_C', 'Embarked_Q', 'Embarked_S',\n",
" 'Cabin_Alone', 'Cabin_Double room', 'Cabin_Four person room',\n",
" 'Cabin_Other', 'Cabin_Three person room', 'Pclass_1', 'Pclass_2',\n",
" 'Pclass_3', 'Cabin symbol_A', 'Cabin symbol_B', 'Cabin symbol_C',\n",
" 'Cabin symbol_D', 'Cabin symbol_E', 'Cabin symbol_F', 'Cabin symbol_G',\n",
" 'Cabin symbol_T'],\n",
" dtype='object')"
]
},
"execution_count": 37,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_train.columns"
]
},
{
"cell_type": "code",
"execution_count": 38,
"id": "b299afb0",
"metadata": {},
"outputs": [],
"source": [
"df_test['Cabin symbol_T'] = 0\n",
"df_test['Cabin_Four person room'] = 0"
]
},
{
"cell_type": "code",
"execution_count": 39,
"id": "5c4f00b0",
"metadata": {},
"outputs": [],
"source": [
"df_train = df_train.reindex(columns=['PassengerId', 'Name', 'Age', 'SibSp', 'Parch', 'Ticket',\n",
" 'Fare', 'Sex_female', 'Embarked_C', 'Embarked_Q', 'Embarked_S',\n",
" 'Cabin_Alone', 'Cabin_Double room', 'Cabin_Four person room',\n",
" 'Cabin_Other', 'Cabin_Three person room', 'Pclass_1', 'Pclass_2',\n",
" 'Pclass_3', 'Cabin symbol_A', 'Cabin symbol_B', 'Cabin symbol_C',\n",
" 'Cabin symbol_D', 'Cabin symbol_E', 'Cabin symbol_F', 'Cabin symbol_G',\n",
" 'Cabin symbol_T', 'Survived'])"
]
},
{
"cell_type": "code",
"execution_count": 40,
"id": "086a50d2",
"metadata": {},
"outputs": [],
"source": [
"df_test = df_test.reindex(columns=['PassengerId', 'Name', 'Age', 'SibSp', 'Parch', 'Ticket',\n",
" 'Fare', 'Sex_female', 'Embarked_C', 'Embarked_Q', 'Embarked_S',\n",
" 'Cabin_Alone', 'Cabin_Double room', 'Cabin_Four person room',\n",
" 'Cabin_Other', 'Cabin_Three person room', 'Pclass_1', 'Pclass_2',\n",
" 'Pclass_3', 'Cabin symbol_A', 'Cabin symbol_B', 'Cabin symbol_C',\n",
" 'Cabin symbol_D', 'Cabin symbol_E', 'Cabin symbol_F', 'Cabin symbol_G',\n",
" 'Cabin symbol_T'])"
]
},
{
"cell_type": "code",
"execution_count": 41,
"id": "55271503",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"PassengerId 0\n",
"Name 0\n",
"Age 0\n",
"SibSp 0\n",
"Parch 0\n",
"Ticket 0\n",
"Fare 0\n",
"Sex_female 0\n",
"Embarked_C 0\n",
"Embarked_Q 0\n",
"Embarked_S 0\n",
"Cabin_Alone 0\n",
"Cabin_Double room 0\n",
"Cabin_Four person room 0\n",
"Cabin_Other 0\n",
"Cabin_Three person room 0\n",
"Pclass_1 0\n",
"Pclass_2 0\n",
"Pclass_3 0\n",
"Cabin symbol_A 0\n",
"Cabin symbol_B 0\n",
"Cabin symbol_C 0\n",
"Cabin symbol_D 0\n",
"Cabin symbol_E 0\n",
"Cabin symbol_F 0\n",
"Cabin symbol_G 0\n",
"Cabin symbol_T 0\n",
"dtype: int64"
]
},
"execution_count": 41,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_test.isna().sum()"
Initian analysis
2023-02-16 13:32:30 +01:00
]
},
{
"cell_type": "markdown",
"id": "7ed9bfbb",
"metadata": {},
"source": [
Bad final predictions
2023-02-17 14:01:05 +01:00
"## Views of the best correlated features"
Initian analysis
2023-02-16 13:32:30 +01:00
]
},
{
"cell_type": "code",
Bad final predictions
2023-02-17 14:01:05 +01:00
"execution_count": 42,
Initian analysis
2023-02-16 13:32:30 +01:00
"id": "3c82db70",
Bad final predictions
2023-02-17 14:01:05 +01:00
"metadata": {
"scrolled": true
},
Initian analysis
2023-02-16 13:32:30 +01:00
"outputs": [
{
"data": {
Bad final predictions
2023-02-17 14:01:05 +01:00
"image/png": "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
Initian analysis
2023-02-16 13:32:30 +01:00
"text/plain": [
"<Figure size 432x288 with 2 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"corrmat = df_train.corr() \n",
Bad final predictions
2023-02-17 14:01:05 +01:00
"cols = corrmat.nlargest(df_train.shape[1], 'Survived')['Survived'].index \n",
Initian analysis
2023-02-16 13:32:30 +01:00
"cm = np.corrcoef(df_train[cols].values.T) \n",
Bad final predictions
2023-02-17 14:01:05 +01:00
"sns.set(font_scale=0.7) \n",
"hm = sns.heatmap(cm, cbar=True, annot=True, square=True, fmt='.2f', annot_kws={'size': 5}, yticklabels=cols.values, xticklabels=cols.values)"
]
},
{
"cell_type": "markdown",
"id": "972b9982",
"metadata": {},
"source": [
"## Model"
]
},
{
"cell_type": "code",
"execution_count": 43,
"id": "f8ff6bbd",
"metadata": {},
"outputs": [],
"source": [
"from sklearn.linear_model import LogisticRegression\n",
"from sklearn.preprocessing import StandardScaler\n",
"from imblearn.over_sampling import RandomOverSampler\n",
"from sklearn.model_selection import train_test_split"
]
},
{
"cell_type": "code",
"execution_count": 44,
"id": "ae38bd90",
"metadata": {},
"outputs": [],
"source": [
"X_train = df_train.drop(['PassengerId', 'Name', 'Ticket', 'Survived'], axis=1)\n",
"y_train = df_train['Survived']\n",
"\n",
"X_test = df_test.drop(['PassengerId', 'Name', 'Ticket'], axis=1)"
]
},
{
"cell_type": "code",
"execution_count": 45,
"id": "79af2916",
"metadata": {},
"outputs": [],
"source": [
"ros = RandomOverSampler()\n",
"X_train, y_train = ros.fit_resample(X_train, y_train)"
]
},
{
"cell_type": "code",
"execution_count": 46,
"id": "5ef85114",
"metadata": {},
"outputs": [],
"source": [
"X_tr, X_val, y_tr, y_val = train_test_split(X_train, y_train, test_size=0.2)"
]
},
{
"cell_type": "code",
"execution_count": 47,
"id": "f93f38a4",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(549, 549)"
]
},
"execution_count": 47,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"len(y_train[y_train==1]), len(y_train[y_train==0])"
]
},
{
"cell_type": "code",
"execution_count": 48,
"id": "09d2817d",
"metadata": {},
"outputs": [],
"source": [
"sc = StandardScaler()\n",
"\n",
"X_train_std = sc.fit_transform(X_tr)\n",
"X_val = sc.transform(X_val)"
]
},
{
"cell_type": "code",
"execution_count": 49,
"id": "96fe96d7",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0.7818181818181819"
]
},
"execution_count": 49,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"clf = LogisticRegression()\n",
"\n",
"clf.fit(X_train_std, y_tr)\n",
"clf.score(X_val, y_val)"
]
},
{
"cell_type": "code",
"execution_count": 50,
"id": "dda1026c",
"metadata": {},
"outputs": [],
"source": [
"X_test = sc.transform(X_test)\n",
"predictions = clf.predict(X_test)"
]
},
{
"cell_type": "code",
"execution_count": 53,
"id": "ea78bc69",
"metadata": {},
"outputs": [],
"source": [
"submissionStacking = pd.DataFrame({ 'PassengerId': df_test[\"PassengerId\"],'Survived': predictions })\n",
"submissionStacking.to_csv(\"submission.csv\", index=False)"
Initian analysis
2023-02-16 13:32:30 +01:00
]
}
],
"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": "3.9.7"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
Reference in New Issue Copy Permalink