def allfeatures_001():
train = classes.get_train_data()
copy = ColumnExtractor(['group_size', 'homeowner', 'car_age', 'age_oldest', 'age_youngest', 'married_couple'])
day = DayTransformer()
state = StateTransformer()
car_val = FillEncoderBinarizer('car_value', 'z')
risk_factor = FillEncoderBinarizer('risk_factor', 0)
c_prev = FillEncoderBinarizer('C_previous', 0)
c_dur = FillEncoderBinarizer('duration_previous', -1)
last_plan = LastObservedPlan()
features = FeatureUnion([
('copy', copy),
('day', day),
('state', state),
('car_val', car_val),
('risk_factor', risk_factor),
('c_prev', c_prev),
('c_dur', c_dur),
# ('last_plan', last_plan)
])
pipeline = Pipeline([
('filter', LastShoppingPointSelector()),
('features', features)
])
train, test = classes.train_test_split(train)
train_x = pipeline.fit_transform(train)
train_y = classes.split_plan(classes.get_actual_plan(train))
y_encoder = classes.MultiColLabelBinarizer()
y = y_encoder.fit_transform(train_y[list('ABCDEFG')])
# Just on one col
est = ExtraTreesClassifier(n_estimators=100, verbose=3)
est.fit(train_x, y)
actuals = classes.split_plan(classes.get_actual_plan(test))
test_x = classes.truncate(test)
test_x = pipeline.transform(test_x)
pred = classes.concatenate_plan(y_encoder.inverse_transform(est.predict(test_x)))
score = classes.score_df(pred, actuals)
scores = classes.col_score_df(pred, actuals)
Can also include some features from the train set
"""
from __future__ import division
import logging
from sklearn.ensemble import RandomForestClassifier
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import OneHotEncoder
import numpy as np
import classes
logger = logging.getLogger('allstate')
logger.info("Loading data")
data = classes.get_train_data()
train, test = classes.train_test_split(data)
# Feature G has the lowest accuracy, so lets use all the other features to predict G
# G takes values of 1, 2, 3, and 4, we'll need to one-hot encode the response
logger.info("Transforming data")
# Transform the data into something that we can give to a learning algorithm
train_y = train.loc[train['record_type'] == 1, 'G']
train_data = train.loc[train['record_type'] == 0, ['customer_ID', 'shopping_pt', 'record_type'] + list('ABCDEFG')]
train_x = classes.get_last_observed_point(train_data)[list('ABCDEFG')]
# Responses need to be encoded to binary columns
y_encoder = OneHotEncoder()
train_y = y_encoder.fit_transform(train_y.reshape((train_y.shape[0], 1))).toarray()
# train_x is a df with columsn A-F