{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# What makes you sound like a female/male"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Data is from Kaggle's [Gender Recognition by Voice](https://www.kaggle.com/primaryobjects/voicegender)"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"xy = pd.read_csv('data/voice.csv')\n",
"\n",
"X = xy.drop('label', axis='columns')\n",
"y = xy['label']"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"from sklearn.model_selection import train_test_split"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"X_train, X_test, y_train, y_test = train_test_split(X, y)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"We'll train a random forest classifier on the entire dataset."
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"from sklearn.ensemble import RandomForestClassifier"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"rf = RandomForestClassifier(n_estimators=100)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini',\n",
" max_depth=None, max_features='auto', max_leaf_nodes=None,\n",
" min_impurity_split=1e-07, min_samples_leaf=1,\n",
" min_samples_split=2, min_weight_fraction_leaf=0.0,\n",
" n_estimators=100, n_jobs=1, oob_score=False, random_state=None,\n",
" verbose=0, warm_start=False)"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"rf.fit(X_train, y_train)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"from sklearn.metrics import accuracy_score"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"0.98232323232323238"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"accuracy_score(y_test, rf.predict(X_test))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Nice! We got over 98% accuracy."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Explaining the classifier"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"from lime.lime_tabular import LimeTabularExplainer"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"features = list(X_train.columns)\n",
"explainer = LimeTabularExplainer(X_train.values, feature_names=features, class_names=['female', 'male'])"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"# randomly pick an example\n",
"example = X_train.sample(1).values[0]"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"exp = explainer.explain_instance(example, rf.predict_proba)"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
"\n",
" \n",
" \n",
" \n",
" \n",
" \n",
" "
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"exp.show_in_notebook()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"This person has less than 0.12 mean fundamental frequency. That's why the model classified this person as a male."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Reference"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"https://github.com/marcotcr/lime"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"---\n",
"**dreamgonfly@gmail.com**"
]
},
{
"cell_type": "markdown",
"metadata": {},
"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": "3.5.1"
}
},
"nbformat": 4,
"nbformat_minor": 0
}