notebook.community

Edit and run



In [103]:

    
import numpy as np
import pandas as pd
from sklearn.linear_model import LinearRegression
from sklearn.preprocessing import StandardScaler



In [104]:

    
def rmse(act, pred):
    return np.sqrt(((act-pred) ** 2).mean())



In [105]:

    
train = pd.read_csv('./regression_train.csv')
test = pd.read_csv('./regression_test.csv')
lrtrain = pd.read_csv('./lr_trainresult.csv')
lrtest = pd.read_csv('./lr_testresult.csv')
caitrain = pd.read_csv('./tttttttttrain.csv')
caitest = pd.read_csv('./tttttttttt.csv')
train['13'] = lrtrain.values
test['13'] = lrtest.values
train['14'] = caitrain.values
test['14'] = caitest.values



In [106]:

    
train.head()



In [107]:

    
'''
train.drop('12', axis=1, inplace=True)
test.drop('12', axis=1, inplace=True)
train.head()
'''









    Out[107]:





"\ntrain.drop('12', axis=1, inplace=True)\ntest.drop('12', axis=1, inplace=True)\ntrain.head()\n"



In [108]:

    
model = LinearRegression().fit(train.iloc[:, 1:], train.iloc[:, 0])
result = model.predict(test.iloc[:, 1:])
#result = np.floor(result)
print(rmse(test.iloc[:, 0], result))
print(result)









    



3.33577057825
[ 84.69009271  80.42153114  81.27666934 ...,  93.25374827  95.46488147
  80.46041455]



In [109]:

    
# 3.47570697131
# 3.46963542896
# 3.33577057825



In [110]:

    
cai = pd.read_csv('./tttttttttt.csv')
rmse(test.iloc[:, 0], cai['cai'].values)









    Out[110]:





3.3445622605544982



In [ ]:

	y	1	2	3	4	5	6	7	8	9	10	11	12	13	14
0	90	6	2	1036	103	114	1.00	1.00	172076	355965	2.0	6527	1851864	90	91.673476
1	88	1	0	2165	205	101	0.40	1.20	43107	44139	3.0	130	1131931	91	90.754319
2	85	62	77	3806	258	166	1.40	1.40	492142	268706	5.2	256	1314590	83	82.319224
3	81	5	0	4721	256	177	0.99	2.58	524787	174964	1.0	233	972606	83	82.775383
4	79	42	55	3949	249	244	2.60	4.60	197289	529200	3.4	331	1013805	73	79.247167