DigitRecognizer

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

dataset=pd.read_csv('input/train.csv')
test=pd.read_csv('input/test.csv')

dataset.describe()

	label	pixel0	pixel1	pixel2	pixel3	pixel4	pixel5	pixel6	pixel7	pixel8	…	pixel774	pixel775	pixel776	pixel777	pixel778	pixel779	pixel780	pixel781	pixel782	pixel783
count	42000.000000	42000	42000	42000	42000	42000	42000	42000	42000	42000	…	42000.000000	42000.000000	42000.000000	42000.00000	42000.000000	42000.000000	42000	42000	42000	42000
mean	4.456643	0	0	0	0	0	0	0	0	0	…	0.219286	0.117095	0.059024	0.02019	0.017238	0.002857	0	0	0	0
std	2.887730	0	0	0	0	0	0	0	0	0	…	6.312890	4.633819	3.274488	1.75987	1.894498	0.414264	0	0	0	0
min	0.000000	0	0	0	0	0	0	0	0	0	…	0.000000	0.000000	0.000000	0.00000	0.000000	0.000000	0	0	0	0
25%	2.000000	0	0	0	0	0	0	0	0	0	…	0.000000	0.000000	0.000000	0.00000	0.000000	0.000000	0	0	0	0
50%	4.000000	0	0	0	0	0	0	0	0	0	…	0.000000	0.000000	0.000000	0.00000	0.000000	0.000000	0	0	0	0
75%	7.000000	0	0	0	0	0	0	0	0	0	…	0.000000	0.000000	0.000000	0.00000	0.000000	0.000000	0	0	0	0
max	9.000000	0	0	0	0	0	0	0	0	0	…	254.000000	254.000000	253.000000	253.00000	254.000000	62.000000	0	0	0	0

8 rows × 785 columns

dataset.head()

	label	pixel0	pixel1	pixel2	pixel3	pixel4	pixel5	pixel6	pixel7	pixel8	…	pixel774	pixel775	pixel776	pixel777	pixel778	pixel779	pixel780	pixel781	pixel782	pixel783
0	1	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
1	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
2	1	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
3	4	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
4	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0

5 rows × 785 columns

test.head()

	pixel0	pixel1	pixel2	pixel3	pixel4	pixel5	pixel6	pixel7	pixel8	pixel9	…	pixel774	pixel775	pixel776	pixel777	pixel778	pixel779	pixel780	pixel781	pixel782	pixel783
0	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
1	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
2	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
3	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
4	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0

5 rows × 784 columns

target=dataset[[0]].values

target

array([[1], [0], [1], …, [7], [6], [9]])

target=target.ravel()

target

array([1, 0, 1, …, 7, 6, 9])

train=dataset.iloc[:,1:].values

train

array([[0, 0, 0, …, 0, 0, 0], [0, 0, 0, …, 0, 0, 0], [0, 0, 0, …, 0, 0, 0], …, [0, 0, 0, …, 0, 0, 0], [0, 0, 0, …, 0, 0, 0], [0, 0, 0, …, 0, 0, 0]])

File “”, line 1 print train.dtype ^ SyntaxError: Missing parentheses in call to ‘print’

test

	pixel0	pixel1	pixel2	pixel3	pixel4	pixel5	pixel6	pixel7	pixel8	pixel9	…	pixel774	pixel775	pixel776	pixel777	pixel778	pixel779	pixel780	pixel781	pixel782	pixel783
0	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
1	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
2	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
3	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
4	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
5	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
6	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
7	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
8	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
9	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
10	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
11	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
12	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
13	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
14	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
15	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
16	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
17	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
18	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
19	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
20	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
21	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
22	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
23	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
24	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
25	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
26	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
27	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
28	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
29	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
…	…	…	…	…	…	…	…	…	…	…	…	…	…	…	…	…	…	…	…	…	…
27970	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
27971	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
27972	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
27973	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
27974	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
27975	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
27976	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
27977	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
27978	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
27979	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
27980	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
27981	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
27982	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
27983	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
27984	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
27985	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
27986	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
27987	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
27988	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
27989	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
27990	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
27991	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
27992	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
27993	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
27994	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
27995	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
27996	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
27997	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
27998	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0
27999	0	0	0	0	0	0	0	0	0	0	…	0	0	0	0	0	0	0	0	0	0

28000 rows × 784 columns

test=test.values

test

array([[0, 0, 0, …, 0, 0, 0], [0, 0, 0, …, 0, 0, 0], [0, 0, 0, …, 0, 0, 0], …, [0, 0, 0, …, 0, 0, 0], [0, 0, 0, …, 0, 0, 0], [0, 0, 0, …, 0, 0, 0]])

#creat and train the random forest
rf=RandomForestClassifier(n_estimators=100)
rf.fit(train,target)

RandomForestClassifier(bootstrap=True, class_weight=None, criterion=’gini’, max_depth=None, max_features=’auto’, max_leaf_nodes=None, min_samples_leaf=1, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=1, oob_score=False, random_state=None, verbose=0, warm_start=False)

pred=rf.predict(test)

pred

array([2, 0, 9, …, 3, 9, 2])

subdemo=pd.read_csv('input/sample_submission.csv')

subdemo

	ImageId	Label
0	1	0
1	2	0
2	3	0
3	4	0
4	5	0
5	6	0
6	7	0
7	8	0
8	9	0
9	10	0
10	11	0
11	12	0
12	13	0
13	14	0
14	15	0
15	16	0
16	17	0
17	18	0
18	19	0
19	20	0
20	21	0
21	22	0
22	23	0
23	24	0
24	25	0
25	26	0
26	27	0
27	28	0
28	29	0
29	30	0
…	…	…
27970	27971	0
27971	27972	0
27972	27973	0
27973	27974	0
27974	27975	0
27975	27976	0
27976	27977	0
27977	27978	0
27978	27979	0
27979	27980	0
27980	27981	0
27981	27982	0
27982	27983	0
27983	27984	0
27984	27985	0
27985	27986	0
27986	27987	0
27987	27988	0
27988	27989	0
27989	27990	0
27990	27991	0
27991	27992	0
27992	27993	0
27993	27994	0
27994	27995	0
27995	27996	0
27996	27997	0
27997	27998	0
27998	27999	0
27999	28000	0

28000 rows × 2 columns

len(test)

28000

len(pred)

28000

np.savetxt('submission_rand_forest.csv', np.c_[range(1,len(test)+1),pred], delimiter=',', header = 'ImageId,Label', comments = '', fmt='%d')