tpot_face_pipeline.py

import numpy as np
import pandas as pd

from sklearn.cross_validation import train_test_split
from sklearn.linear_model import LogisticRegression

# NOTE: Make sure that the class is labeled 'class' in the data file
tpot_data = pd.read_csv('PATH/TO/DATA/FILE', sep='COLUMN_SEPARATOR')
training_indices, testing_indices = train_test_split(tpot_data.index, stratify = tpot_data['class'].values, train_size=0.75, test_size=0.25)


result1 = tpot_data.copy()

# Perform classification with a logistic regression classifier
lrc1 = LogisticRegression(C=0.01)
lrc1.fit(result1.loc[training_indices].drop('class', axis=1).values, result1.loc[training_indices, 'class'].values)
result1['lrc1-classification'] = lrc1.predict(result1.drop('class', axis=1).values)

# Perform classification with a logistic regression classifier
lrc2 = LogisticRegression(C=100.0)
lrc2.fit(result1.loc[training_indices].drop('class', axis=1).values, result1.loc[training_indices, 'class'].values)
result2 = result1.copy()
result2['lrc2-classification'] = lrc2.predict(result2.drop('class', axis=1).values)