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")

# 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

from sklearn.neighbors import KNeighborsClassifier


train.loc[:,'pixel0':] =  train.loc[:,'pixel0':] * 1.0/255.0
test.loc[:,'pixel0':] =  test.loc[:,'pixel0':] * 1.0/255.0
import random
train = train.sample(n=4200)
test = test.sample(n=2800)

# alg = LogisticRegression(random_state=1)
alg = KNeighborsClassifier(n_neighbors=3)
print("training")
alg.fit(train.loc[:,'pixel0':], train.loc[:,'label'])
print("predicting")
predictions = alg.predict(test)

submission = pd.DataFrame({"ImageId": range(1,test.shape[0]+1),
    "label": predictions})

submission.to_csv("kaggle.csv", index=False)