import pandas as pd
import time
from sklearn.ensemble import RandomForestClassifier
from IO import Input
from IO import Output
start_time = time.time()
# load train data
df_trainset_caf = Input.load_trainset_caffefeatures()
df_trainset_lab = Input.load_trainset_labels()
# Load test data
df_validationset_caf = Input.load_validationset_caffefeatures()
print("--- load data: %s seconds ---" % round((time.time() - start_time),2))
start_time = time.time()
x_train = df_trainset_caf
y_train = df_trainset_lab
x_test = df_validationset_caf
# Train model
rf = RandomForestClassifier(n_estimators=500)
rf.fit(x_train, y_train)
print("--- train model: %s seconds ---" % round((time.time() - start_time),2))
start_time = time.time()
# Predict
'''Simple test file to test whether loading caffefeatures works properly. Selecting percentiles, selecting rows and giving error messages.
@author: Diede Kemper'''
from IO import Input
features = Input.load_validationset_caffefeatures()
print features.shape
print 'should be: 8061x3983'
features = Input.load_traindata_caffefeatures(userows=range(3000, 5500))
print features.shape
print 'should be: 2500x3983'
features = Input.load_validationset_caffefeatures(
featureSelectionMethod='chi2', Percentile=100)
print features.shape
print 'should be: 8061x3983'
features = Input.load_validationset_caffefeatures(featureSelectionMethod='hoi',
Percentile=90)
print features.shape
print 'should print error message'
features = Input.load_validationset_caffefeatures(
featureSelectionMethod='chi2', Percentile=210)
print features.shape
print 'should print error message'
features = Input.load_traindata_caffefeatures(featureSelectionMethod='chi2',
Percentile=5)
print features.shape