import numpy as np
import pandas as pd
#from Output import *
import pickle
#import xgboost as xgb
print('loading data')
#Load data
x_traindata = pd.read_csv('HOG_features_train_8_16_1.csv',
sep=',',
header=None).values
x_testdata = pd.read_csv('HOG_features_test_8_16_1.csv', sep=',',
header=None).values
#load classification
y_traindata = np.asarray(Input.load_traindata_labels())
print('training classifier')
#Train classifier
clf = OneVsRestClassifier(SVC(kernel='poly', probability=True))
clf.fit(x_traindata, y_traindata)
# now you can save it to a file
with open('classifierpolytraindata_HOG_8_16_1.pkl', 'wb') as f:
pickle.dump(clf, f)
## and later you can load it
with open('classifierpolytraindata_HOG_8_16_1.pkl', 'rb') as f:
clf = pickle.load(f)
#Make predictions
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_traindata_caf = Input.load_traindata_caffefeatures()
df_traindata_lab = Input.load_traindata_labels()
# Load test data
df_testdata_caf = Input.load_testdata_caffefeatures()
print("--- load data: %s seconds ---" % round((time.time() - start_time), 2))
start_time = time.time()
x_train = df_traindata_caf
y_train = df_traindata_lab
x_test = df_testdata_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