import pandas as pd
import numpy as np
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
train = pd.read_csv('../input/digit-recognizer/train.csv')
test = pd.read_csv('../input/digit-recognizer/test.csv')
train.shape, test.shape
((42000, 785), (28000, 784))
images = train.iloc[:,1:]
labels = train.iloc[:,:1]
images.shape, labels.shape, test.shape
((42000, 784), (42000, 1), (28000, 784))
train_images, valid_images, train_labels, valid_labels = train_test_split(images, labels, train_size=0.8, test_size=0.2, random_state=0)
train_images.shape, valid_images.shape
((33600, 784), (8400, 784))
clf = RandomForestClassifier(random_state=0)
clf.fit(train_images.values, train_labels.values.ravel())
RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=1, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=10, n_jobs=1, oob_score=False, random_state=0, verbose=0, warm_start=False)
clf.score(valid_images, valid_labels)
0.93690476190476191
predictions = clf.predict(test)
submissions = pd.DataFrame({
"ImageId": list(range(1, len(predictions)+1)),
"Label": predictions})
submissions.to_csv("output.csv", index=False, header=True)