{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"import pandas as pd\n",
"import os\n",
"from sklearn.model_selection import train_test_split\n",
"from sklearn.ensemble import RandomForestClassifier\n",
"from sklearn import metrics\n",
"import seaborn as sns"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"
\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" PassengerId | \n",
" Survived | \n",
" Pclass | \n",
" Name | \n",
" Sex | \n",
" Age | \n",
" SibSp | \n",
" Parch | \n",
" Ticket | \n",
" Fare | \n",
" Cabin | \n",
" Embarked | \n",
"
\n",
" \n",
" \n",
" \n",
" 0 | \n",
" 1 | \n",
" 0 | \n",
" 3 | \n",
" Braund, Mr. Owen Harris | \n",
" male | \n",
" 22.0 | \n",
" 1 | \n",
" 0 | \n",
" A/5 21171 | \n",
" 7.2500 | \n",
" NaN | \n",
" S | \n",
"
\n",
" \n",
" 1 | \n",
" 2 | \n",
" 1 | \n",
" 1 | \n",
" Cumings, Mrs. John Bradley (Florence Briggs Th... | \n",
" female | \n",
" 38.0 | \n",
" 1 | \n",
" 0 | \n",
" PC 17599 | \n",
" 71.2833 | \n",
" C85 | \n",
" C | \n",
"
\n",
" \n",
" 2 | \n",
" 3 | \n",
" 1 | \n",
" 3 | \n",
" Heikkinen, Miss. Laina | \n",
" female | \n",
" 26.0 | \n",
" 0 | \n",
" 0 | \n",
" STON/O2. 3101282 | \n",
" 7.9250 | \n",
" NaN | \n",
" S | \n",
"
\n",
" \n",
" 3 | \n",
" 4 | \n",
" 1 | \n",
" 1 | \n",
" Futrelle, Mrs. Jacques Heath (Lily May Peel) | \n",
" female | \n",
" 35.0 | \n",
" 1 | \n",
" 0 | \n",
" 113803 | \n",
" 53.1000 | \n",
" C123 | \n",
" S | \n",
"
\n",
" \n",
" 4 | \n",
" 5 | \n",
" 0 | \n",
" 3 | \n",
" Allen, Mr. William Henry | \n",
" male | \n",
" 35.0 | \n",
" 0 | \n",
" 0 | \n",
" 373450 | \n",
" 8.0500 | \n",
" NaN | \n",
" S | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" PassengerId Survived Pclass \\\n",
"0 1 0 3 \n",
"1 2 1 1 \n",
"2 3 1 3 \n",
"3 4 1 1 \n",
"4 5 0 3 \n",
"\n",
" Name Sex Age SibSp \\\n",
"0 Braund, Mr. Owen Harris male 22.0 1 \n",
"1 Cumings, Mrs. John Bradley (Florence Briggs Th... female 38.0 1 \n",
"2 Heikkinen, Miss. Laina female 26.0 0 \n",
"3 Futrelle, Mrs. Jacques Heath (Lily May Peel) female 35.0 1 \n",
"4 Allen, Mr. William Henry male 35.0 0 \n",
"\n",
" Parch Ticket Fare Cabin Embarked \n",
"0 0 A/5 21171 7.2500 NaN S \n",
"1 0 PC 17599 71.2833 C85 C \n",
"2 0 STON/O2. 3101282 7.9250 NaN S \n",
"3 0 113803 53.1000 C123 S \n",
"4 0 373450 8.0500 NaN S "
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = pd.read_csv(\"titanic/train.csv\")\n",
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" Survived | \n",
" Pclass | \n",
" Age | \n",
" SibSp | \n",
" Parch | \n",
" Fare | \n",
" Sex_female | \n",
" Sex_male | \n",
" Embarked_C | \n",
" Embarked_Q | \n",
" Embarked_S | \n",
"
\n",
" \n",
" \n",
" \n",
" 0 | \n",
" 0 | \n",
" 3 | \n",
" 22.0 | \n",
" 1 | \n",
" 0 | \n",
" 7.2500 | \n",
" 0 | \n",
" 1 | \n",
" 0 | \n",
" 0 | \n",
" 1 | \n",
"
\n",
" \n",
" 1 | \n",
" 1 | \n",
" 1 | \n",
" 38.0 | \n",
" 1 | \n",
" 0 | \n",
" 71.2833 | \n",
" 1 | \n",
" 0 | \n",
" 1 | \n",
" 0 | \n",
" 0 | \n",
"
\n",
" \n",
" 2 | \n",
" 1 | \n",
" 3 | \n",
" 26.0 | \n",
" 0 | \n",
" 0 | \n",
" 7.9250 | \n",
" 1 | \n",
" 0 | \n",
" 0 | \n",
" 0 | \n",
" 1 | \n",
"
\n",
" \n",
" 3 | \n",
" 1 | \n",
" 1 | \n",
" 35.0 | \n",
" 1 | \n",
" 0 | \n",
" 53.1000 | \n",
" 1 | \n",
" 0 | \n",
" 0 | \n",
" 0 | \n",
" 1 | \n",
"
\n",
" \n",
" 4 | \n",
" 0 | \n",
" 3 | \n",
" 35.0 | \n",
" 0 | \n",
" 0 | \n",
" 8.0500 | \n",
" 0 | \n",
" 1 | \n",
" 0 | \n",
" 0 | \n",
" 1 | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" Survived Pclass Age SibSp Parch Fare Sex_female Sex_male \\\n",
"0 0 3 22.0 1 0 7.2500 0 1 \n",
"1 1 1 38.0 1 0 71.2833 1 0 \n",
"2 1 3 26.0 0 0 7.9250 1 0 \n",
"3 1 1 35.0 1 0 53.1000 1 0 \n",
"4 0 3 35.0 0 0 8.0500 0 1 \n",
"\n",
" Embarked_C Embarked_Q Embarked_S \n",
"0 0 0 1 \n",
"1 1 0 0 \n",
"2 0 0 1 \n",
"3 0 0 1 \n",
"4 0 0 1 "
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# drop features\n",
"for f in ['Name', 'Ticket', 'Cabin', 'PassengerId']:\n",
" df = df.drop(f,axis=1)\n",
"\n",
"# converts categorical variables into dummy/indicator variables\n",
"df_ = pd.get_dummies(df)\n",
"\n",
"# fill in null values\n",
"df_ = df_.fillna(df_.mean())\n",
"df_.head()"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
""
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "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\n",
"text/plain": [
""
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"# do some visualization of the dataframe, because violinplots are pretty\n",
"sns.catplot(data=df, kind='violin', hue='Survived', x ='Embarked', y ='Age', col='Sex')"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" Survived | \n",
" Pclass | \n",
" Age | \n",
" SibSp | \n",
" Parch | \n",
" Fare | \n",
" Sex_female | \n",
" Sex_male | \n",
" Embarked_C | \n",
" Embarked_Q | \n",
" Embarked_S | \n",
"
\n",
" \n",
" \n",
" \n",
" 231 | \n",
" 0 | \n",
" 3 | \n",
" 29.000000 | \n",
" 0 | \n",
" 0 | \n",
" 7.7750 | \n",
" 0 | \n",
" 1 | \n",
" 0 | \n",
" 0 | \n",
" 1 | \n",
"
\n",
" \n",
" 836 | \n",
" 0 | \n",
" 3 | \n",
" 21.000000 | \n",
" 0 | \n",
" 0 | \n",
" 8.6625 | \n",
" 0 | \n",
" 1 | \n",
" 0 | \n",
" 0 | \n",
" 1 | \n",
"
\n",
" \n",
" 639 | \n",
" 0 | \n",
" 3 | \n",
" 29.699118 | \n",
" 1 | \n",
" 0 | \n",
" 16.1000 | \n",
" 0 | \n",
" 1 | \n",
" 0 | \n",
" 0 | \n",
" 1 | \n",
"
\n",
" \n",
" 389 | \n",
" 1 | \n",
" 2 | \n",
" 17.000000 | \n",
" 0 | \n",
" 0 | \n",
" 12.0000 | \n",
" 1 | \n",
" 0 | \n",
" 1 | \n",
" 0 | \n",
" 0 | \n",
"
\n",
" \n",
" 597 | \n",
" 0 | \n",
" 3 | \n",
" 49.000000 | \n",
" 0 | \n",
" 0 | \n",
" 0.0000 | \n",
" 0 | \n",
" 1 | \n",
" 0 | \n",
" 0 | \n",
" 1 | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" Survived Pclass Age SibSp Parch Fare Sex_female Sex_male \\\n",
"231 0 3 29.000000 0 0 7.7750 0 1 \n",
"836 0 3 21.000000 0 0 8.6625 0 1 \n",
"639 0 3 29.699118 1 0 16.1000 0 1 \n",
"389 1 2 17.000000 0 0 12.0000 1 0 \n",
"597 0 3 49.000000 0 0 0.0000 0 1 \n",
"\n",
" Embarked_C Embarked_Q Embarked_S \n",
"231 0 0 1 \n",
"836 0 0 1 \n",
"639 0 0 1 \n",
"389 1 0 0 \n",
"597 0 0 1 "
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# stratify into training, testing\n",
"train,test=train_test_split(df_,test_size=0.3,random_state=0, stratify=df_['Survived'])\n",
"train.head()"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Processed DataFrame for Training : Survived is the Target, other columns are features.\n"
]
},
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" Survived | \n",
" Pclass | \n",
" Age | \n",
" SibSp | \n",
" Parch | \n",
" Fare | \n",
" Sex_female | \n",
" Sex_male | \n",
" Embarked_C | \n",
" Embarked_Q | \n",
" Embarked_S | \n",
"
\n",
" \n",
" \n",
" \n",
" 231 | \n",
" 0 | \n",
" 3 | \n",
" 29.000000 | \n",
" 0 | \n",
" 0 | \n",
" 7.7750 | \n",
" 0 | \n",
" 1 | \n",
" 0 | \n",
" 0 | \n",
" 1 | \n",
"
\n",
" \n",
" 836 | \n",
" 0 | \n",
" 3 | \n",
" 21.000000 | \n",
" 0 | \n",
" 0 | \n",
" 8.6625 | \n",
" 0 | \n",
" 1 | \n",
" 0 | \n",
" 0 | \n",
" 1 | \n",
"
\n",
" \n",
" 639 | \n",
" 0 | \n",
" 3 | \n",
" 29.699118 | \n",
" 1 | \n",
" 0 | \n",
" 16.1000 | \n",
" 0 | \n",
" 1 | \n",
" 0 | \n",
" 0 | \n",
" 1 | \n",
"
\n",
" \n",
" 389 | \n",
" 1 | \n",
" 2 | \n",
" 17.000000 | \n",
" 0 | \n",
" 0 | \n",
" 12.0000 | \n",
" 1 | \n",
" 0 | \n",
" 1 | \n",
" 0 | \n",
" 0 | \n",
"
\n",
" \n",
" 597 | \n",
" 0 | \n",
" 3 | \n",
" 49.000000 | \n",
" 0 | \n",
" 0 | \n",
" 0.0000 | \n",
" 0 | \n",
" 1 | \n",
" 0 | \n",
" 0 | \n",
" 1 | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" Survived Pclass Age SibSp Parch Fare Sex_female Sex_male \\\n",
"231 0 3 29.000000 0 0 7.7750 0 1 \n",
"836 0 3 21.000000 0 0 8.6625 0 1 \n",
"639 0 3 29.699118 1 0 16.1000 0 1 \n",
"389 1 2 17.000000 0 0 12.0000 1 0 \n",
"597 0 3 49.000000 0 0 0.0000 0 1 \n",
"\n",
" Embarked_C Embarked_Q Embarked_S \n",
"231 0 0 1 \n",
"836 0 0 1 \n",
"639 0 0 1 \n",
"389 1 0 0 \n",
"597 0 0 1 "
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"# create X_train,Y_train, Y_train,X_test\n",
"X_train = train.drop(['Survived'],axis=1)\n",
"Y_train = train['Survived']\n",
"X_test = test.drop(['Survived'], axis=1)\n",
"Y_test = test['Survived']\n",
"\n",
"# Display\n",
"print(\"Processed DataFrame for Training : Survived is the Target, other columns are features.\")\n",
"display(train.head())\n"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Accuracy:\t 0.8134328358208955\n"
]
}
],
"source": [
"# Random Forest\n",
"random_forest = RandomForestClassifier(n_estimators=100)\n",
"random_forest.fit(X_train, Y_train)\n",
"random_forest_preds = random_forest.predict(X_test)\n",
"\n",
"print('Accuracy:\\t', metrics.accuracy_score(random_forest_preds,Y_test))"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"import lime \n",
"import lime.lime_tabular"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [],
"source": [
"X = X_train.values\n",
"predict_fn = lambda x: random_forest.predict_proba(x).astype(float)\n",
"explainer = lime.lime_tabular.LimeTabularExplainer(X,feature_names = X_train.columns,\n",
" class_names=['Will Die','Will Survive'],kernel_width=5)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" Survived | \n",
" Pclass | \n",
" Age | \n",
" SibSp | \n",
" Parch | \n",
" Fare | \n",
" Sex_female | \n",
" Sex_male | \n",
" Embarked_C | \n",
" Embarked_Q | \n",
" Embarked_S | \n",
"
\n",
" \n",
" \n",
" \n",
" 421 | \n",
" 0 | \n",
" 3 | \n",
" 21.0 | \n",
" 0 | \n",
" 0 | \n",
" 7.7333 | \n",
" 0 | \n",
" 1 | \n",
" 0 | \n",
" 1 | \n",
" 0 | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" Survived Pclass Age SibSp Parch Fare Sex_female Sex_male \\\n",
"421 0 3 21.0 0 0 7.7333 0 1 \n",
"\n",
" Embarked_C Embarked_Q Embarked_S \n",
"421 0 1 0 "
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# look at an unlucky passenger\n",
"test.loc[[421]]"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
" \n",
" \n",
" \n",
" \n",
" \n",
" "
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"#what happens to this person in our model?\n",
"unlucky = X_test.loc[[421]].values[0]\n",
"exp = explainer.explain_instance(unlucky,predict_fn,num_features=10)\n",
"exp.show_in_notebook(show_all=False)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Interpretation:**\n",
"Model predicted \"Not Survived\", and hte biggest effect is the person being male. Also, being a passenger class 3 decreases his chance of survival, but his age increases it. "
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" Survived | \n",
" Pclass | \n",
" Age | \n",
" SibSp | \n",
" Parch | \n",
" Fare | \n",
" Sex_female | \n",
" Sex_male | \n",
" Embarked_C | \n",
" Embarked_Q | \n",
" Embarked_S | \n",
"
\n",
" \n",
" \n",
" \n",
" 310 | \n",
" 1 | \n",
" 1 | \n",
" 24.0 | \n",
" 0 | \n",
" 0 | \n",
" 83.1583 | \n",
" 1 | \n",
" 0 | \n",
" 1 | \n",
" 0 | \n",
" 0 | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" Survived Pclass Age SibSp Parch Fare Sex_female Sex_male \\\n",
"310 1 1 24.0 0 0 83.1583 1 0 \n",
"\n",
" Embarked_C Embarked_Q Embarked_S \n",
"310 1 0 0 "
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"test.loc[[310]]"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
" \n",
" \n",
" \n",
" \n",
" \n",
" "
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"lucky = X_test.loc[[310]].values[0]\n",
"exp = explainer.explain_instance(lucky, predict_fn,num_features=10)\n",
"exp.show_in_notebook(show_all=False)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"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": "3.8.5"
}
},
"nbformat": 4,
"nbformat_minor": 4
}