Kaggle まとめ: BOSCH (intro + forum discussion) ref: http://qiita.com/TomHortons/items/e8a7cea90226bd5ed32f

check_category.py

cat_cols = pd.read_csv(TRAIN_CAT, nrows = 1).columns.values
print 'cat_cols: ', cat_cols
print 'cat_cols.shape: ', cat_cols.shape

cats = pd.read_csv(TRAIN_CAT, usecols=(cat_cols[:2].tolist()))
print 'cats.shape: ', cats.shape
print cats

check_date.py

date_cols = pd.read_csv(TRAIN_DATE, nrows = 1).columns.values
date = pd.read_csv(TRAIN_DATE, usecols=(date_cols[:2].tolist()))

print 'date_cols.shape: ', date_cols.shape
print date_cols
print 'date.shape: ', date.shape
print date

check_numeric.py

import numpy as np
import pandas as pd

numeric_cols = pd.read_csv(TRAIN_NUMERIC, nrows = 1).columns.values
print numeric_cols
print 'cols.shape: ', numeric_cols.shape

F0 = pd.read_csv(TRAIN_NUMERIC, usecols=(numeric_cols[:2].tolist() + ['Response']))
print 'F0.shape: ', F0.shape

file0.txt

Id,Response
1,0
2,1
3,0
etc.

file2.txt

array(['Id', 'L0_S0_F0', 'L0_S0_F2', 'L0_S0_F4', 'L0_S0_F6', 'L0_S0_F8',
       'L0_S0_F10', 'L0_S0_F12', 'L0_S0_F14', 'L0_S0_F16', 'L0_S0_F18',
       'L0_S0_F20', 'L0_S0_F22', 'L0_S1_F24', 'L0_S1_F28', 'L0_S2_F32',
       'L0_S2_F36', 'L0_S2_F40', 'L0_S2_F44', 'L0_S2_F48', 'L0_S2_F52',
       'L0_S2_F56', 'L0_S2_F60', 'L0_S2_F64', 'L0_S3_F68', 'L0_S3_F72',
       .....
       'L3_S50_F4245', 'L3_S50_F4247', 'L3_S50_F4249', 'L3_S50_F4251',
       'L3_S50_F4253', 'L3_S51_F4256', 'L3_S51_F4258', 'L3_S51_F4260',
       'L3_S51_F4262', 'Response'], dtype=object)
cols.shape:  (970,)
F0.shape:  (1183747, 2)

file3.txt

              Id  L0_S0_F0  Response
0              4     0.030         0
1              6       NaN         0
2              7     0.088         0
3              9    -0.036         0

file5.txt

cat_cols: ['Id' 'L0_S1_F25' 'L0_S1_F27' ..., 'L3_S49_F4237' 'L3_S49_F4239'
 'L3_S49_F4240']

cat_cols.shape:  (2141,)

cats.shape:  (1183747, 2)

              Id L0_S1_F25
0              4       NaN
1              6       NaN
2              7       NaN
3              9       NaN
4             11       NaN
5             13       NaN
6             14       NaN
7             16       NaN
8             18       NaN

file7.txt

date_cols.shape:  (1157,)
['Id' 'L0_S0_D1' 'L0_S0_D3' ..., 'L3_S51_D4259' 'L3_S51_D4261'
 'L3_S51_D4263']
date.shape:  (1183747, 2)
              Id  L0_S0_D1
0              4     82.24
1              6       NaN
2              7   1618.70
3              9   1149.20
4             11    602.64
5             13   1331.66

file8.txt

from scipy import stats
import pandas as pd
import numpy as np
import matplotlib as mpl
mpl.use('Agg')
import matplotlib.pyplot as plt
import seaborn as sns


DATA_DIR = "../input"


TRAIN_NUMERIC = "{0}/train_numeric.csv".format(DATA_DIR)
TEST_NUMERIC = "{0}/test_numeric.csv".format(DATA_DIR)

COL_BATCH = 100
numeric_cols = pd.read_csv(TRAIN_NUMERIC, nrows = 1).columns.values

for n_ in range(len(numeric_cols)/COL_BATCH):
    cols = numeric_cols[(n_*COL_BATCH):(n_*COL_BATCH+COL_BATCH)].tolist()
    train = pd.read_csv(TRAIN_NUMERIC, index_col = 0, usecols=(cols + ['Response']))
    X_neg, X_pos = train[train['Response'] == 0].iloc[:, :-1], train[train['Response']==1].iloc[:, :-1]

    BATCH_SIZE = 10
    dummy = []
    source = train.drop('Response', axis=1)

    for n in list(range(0, train.shape[1], BATCH_SIZE)):
        data = source.iloc[:, n:n+BATCH_SIZE]
        data_cols = data.columns.tolist()
        dummy.append(pd.melt(pd.concat([data, train.Response], axis=1), id_vars = 'Response', value_vars = data_cols))

    FIGSIZE = (3*(BATCH_SIZE),4*(COL_BATCH/BATCH_SIZE))
    _, axs = plt.subplots(len(dummy), figsize = FIGSIZE)
    for data, ax in zip(dummy, axs):
        v_plots = sns.violinplot(x = 'variable',  y = 'value', hue = 'Response', data = data, ax = ax, split =True)
    v_plots.get_figure().savefig("violin_{0}.jpg".format(n_))

file9.txt

import pandas as pd
import numpy as np
import seaborn as sns

features_names = [
    'L0_S11_F298', 'L1_S24_F1672', 'L1_S24_F766', 'L1_S24_F1844',
    'L1_S24_F1632', 'L1_S24_F1723', 'L1_S24_F1846', 'L1_S25_F2761',
    'L1_S25_F2193'
]
features = pd.read_csv(TRAIN_NUMERIC, index_col = 0, usecols=(features_names + ['Response'])).reset_index()
for f in features.columns[:-1]:
    features[f][np.isnan(features[f])] = features[f].median()

X_neg, X_pos = features[features['Response'] == 0], features[features['Response']==1]
volumes = len(X_pos) if len(X_pos)<len(X_neg) else len(X_neg)
features = pd.concat([X_pos, X_neg]).reset_index(drop=True)
g = sns.pairplot(features, hue="Response", vars=test.columns.tolist()[:-1], markers='.')