#make字段異常值清洗
new = data[['make', 'model', 'instance_id']]
new['make_model'] = new['make']+':::'+new['model']
new.head(3)

# new.make_model.value_counts()
# 統(tǒng)計(jì)make_model列屬性值出現(xiàn)的次數(shù)
 
 
 
new.make_model.value_counts()[new.make_model.value_counts() <= 200]
 
"""
OPPO:::OPPO+A59st               200
OPPO:::3007                     200
Xiaomi:::Redmi%20Note%203       200
Meizu:::MEIZU-M6                199
samsung:::SM-N9006              199
                               ... 
OPPO,OPPO A53,A53:::OPPO A53      1
boway U15:::boway U15             1
BaiMao:::BM I8                    1
vivo:::vivoy75a                   1
SUPERJO:::SUPERJO                 1
Name: make_model, Length: 15597, dtype: int64
"""

(new.make_model.value_counts()[new.make_model.value_counts() <= 200]).index
 
"""
Index(['OPPO:::OPPO+A59st', 'OPPO:::3007', 'Xiaomi:::Redmi%20Note%203',
       'Meizu:::MEIZU-M6', 'samsung:::SM-N9006', 'Coolpad:::MTS-T0',
       'OPPO R11st:::OPPO R11st', 'Blephone:::lephone T7A', 'GIONEE:::GN9011',
       'Meizu:::PRO 7-S',
       ...
       'HUAWEI:::HUAWEI%25252BG7-UL20', 'VOLTE:::L3', 'GIONEE:::GN868',
       'alps:::SOP-i9', 'GT-I9300I:::GT-I9300I',
       'OPPO,OPPO A53,A53:::OPPO A53', 'boway U15:::boway U15',
       'BaiMao:::BM I8', 'vivo:::vivoy75a', 'SUPERJO:::SUPERJO'],
      dtype='object', length=15597)
"""
 

new.make_model
 
"""
0          HUAWEI:::HUAWEI-CAZ-AL10
1             Xiaomi:::Redmi Note 4
2                  OPPO:::OPPO+R11s
3                               NaN
4                  Apple:::iPhone 7
                     ...           
1041669             OPPO:::OPPO-R9s
1041670              Xiaomi:::MI-5X
1041671             vivo:::vivo Y37
1041672          vivo:::vivo%20Y75A
1041673                  OPPO:::A31
Name: make_model, Length: 1041674, dtype: object
"""

# 在make_model列，
# 定位符合 new.make_model.isin((new.make_model.value_counts()[new.make_model.value_counts() <= 200]).index) 的行
 
# 
 
new.loc[new.make_model.isin((new.make_model.value_counts()[new.make_model.value_counts() <= 200]).index), 'make_model'] = 'other' #去除低頻詞

data['day'] = data['time'].apply(lambda x : int(time.strftime("%d", time.localtime(x))))
data['period'] = data['day']
data[['period']].head(3)

data['period'].unique()
 
# array([29, 30, 31, 27,  1,  2, 28,  3])

[data['period']<27]
 
"""
[0          False
 1          False
 2          False
 3          False
 4          False
            ...  
 1041669     True
 1041670     True
 1041671     True
 1041672     True
 1041673     True
 Name: period, Length: 1041674, dtype: bool]
"""

 
data['period']<27
 
"""
0          False
1          False
2          False
3          False
4          False
           ...  
1041669     True
1041670     True
1041671     True
1041672     True
1041673     True
Name: period, Length: 1041674, dtype: bool
"""

data['period'][data['period']<27]
 
"""
950        1
951        1
952        1
953        1
954        1
          ..
1041669    3
1041670    3
1041671    3
1041672    3
1041673    3
Name: period, Length: 348536, dtype: int64
"""
 
 
data['period'][data['period']<27] = data['period'][data['period']<27] + 31

data[['period']][data['period']<27].head(3)

t2['receive_number'] = t2.date_received.apply(lambda s:len(s.split(':')))
t2 = t2[t2.receive_number>1]
t2.head(3)