import pandas as pd

# The competition datafiles are in the directory ../input
# Read competition data files:
train = pd.read_csv("../input/train.csv")
test  = pd.read_csv("../input/test.csv")
#ref   = pd.read_csv("../input/sample_submission.csv")
from sklearn.ensemble import RandomForestClassifier
print('start')
model_train = train.loc[:,'pixel0':'pixel783']
model_label = train.loc[:,'label']
model_test = test.loc[:,'pixel0':'pixel783']
#model_ref = ref.loc[:,'label']
# Write to the log:
#print("Training set has {0[0]} rows and {0[1]} columns".format(train.shape))
#print("Test set has {0[0]} rows and {0[1]} columns".format(test.shape))
# Any files you write to the current directory get shown as outputs
rfc = RandomForestClassifier(n_estimators=2000,n_jobs=4)
rfc.fit(model_train,model_label)
print('fitend')
model_pred = rfc.predict(model_test)
print('predictend')
imageid = [i for i in range(1,(len(model_pred)+1))]
outfile = pd.DataFrame({'label':model_pred},index=imageid)
outfile.to_csv('output.csv')
#error = 0
#for i in range(0,len(model_pred)):
#    if(model_pred[i]!=model_ref[i]):
#        error = error + 1
#print('error')
#print(float(error)/len(model_pred))