Kaggle | Digit Recognizer

digit_recognizer_1.py

""" First attempt at Kaggle Digit Recognizer | https://www.kaggle.com/c/digit-recognizer/
    Basic approach w/ random trees results in 0.96486 accuracy
"""


import pandas as pd
import numpy as np
from numpy import savetxt
from sklearn.ensemble import RandomForestClassifier

# import data
train = pd.read_csv('train.csv')
test = pd.read_csv('test.csv')

# format Y
Y = train['label']
Y = Y.values.tolist()

# format X
X = train.drop('label', axis=1)
X = X.values.tolist()

# fit the model
rf = RandomForestClassifier(n_estimators=100)
print rf # see if it works
rf.fit(X,Y) # fits in place, right?

# trying out predict
prediction = rf.predict(test).tolist()
index = range(1,2801)

# create output csv

np.savetxt('prediction.csv', (index,prediction), delimiter=' ')