import pandas as pd
from pandas import Series, DataFrame
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import RandomForestClassifier

# The competition datafiles are in the directory ../input
# Read competition data files:
train = pd.read_csv("../input/train.csv")
train.drop(train.tail(32000).index, inplace=True)
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
train.head()
X_Train = train.drop("label",axis = 1)
Y_Train = train["label"]
X_Test = test

rf = RandomForestClassifier()
rf.fit(X_Train,Y_Train)
print(rf.score(X_Train,Y_Train))
Y_Pred = rf.predict(X_Test)

submission = DataFrame(Y_Pred, columns=['Label'], 
                       index=np.arange(1, 28001))
submission.to_csv("rf.csv")