In [2]:
import pandas as pd
import numpy as np
In [59]:
df = pd.read_csv("daily users.csv",parse_dates=True)
In [60]:
df.head()
Out[60]:
Day
Users
0
5/1/15
40,434
1
5/2/15
26,132
2
5/3/15
32,169
3
5/4/15
35,586
4
5/5/15
35,365
In [61]:
df.columns
Out[61]:
Index([u'Day', u'Users'], dtype='object')
In [ ]:
In [62]:
df["Day"] = pd.to_datetime(df["Day"])
In [63]:
df["Day"].dtype
Out[63]:
dtype('<M8[ns]')
In [64]:
Out[64]:
Day
Users
In [65]:
df_masked = df[(df.Day > '2015-05-01') & (df.Day < '2015-05-05')]
In [69]:
df
Out[69]:
Day
Users
0
2015-05-01
40,434
1
2015-05-02
26,132
2
2015-05-03
32,169
3
2015-05-04
35,586
4
2015-05-05
35,365
5
2015-05-06
33,851
6
2015-05-07
38,475
7
2015-05-08
54,304
8
2015-05-09
52,073
9
2015-05-10
42,085
10
2015-05-11
46,599
11
2015-05-12
66,755
12
2015-05-13
60,469
13
2015-05-14
45,566
14
2015-05-15
53,777
15
2015-05-16
36,404
16
2015-05-17
34,246
17
2015-05-18
51,926
18
2015-05-19
61,802
19
2015-05-20
64,421
20
2015-05-21
65,658
21
2015-05-22
43,693
22
2015-05-23
37,892
23
2015-05-24
34,667
24
2015-05-25
31,375
25
2015-05-26
48,070
26
2015-05-27
116,569
27
2015-05-28
157,395
28
2015-05-29
59,278
29
2015-05-30
58,530
...
...
...
243
2015-12-30
97,197
244
2015-12-31
78,765
245
2016-01-01
84,231
246
2016-01-02
63,889
247
2016-01-03
54,588
248
2016-01-04
84,144
249
2016-01-05
100,541
250
2016-01-06
232,881
251
2016-01-07
181,296
252
2016-01-08
105,137
253
2016-01-09
82,520
254
2016-01-10
79,769
255
2016-01-11
94,185
256
2016-01-12
112,466
257
2016-01-13
104,724
258
2016-01-14
96,629
259
2016-01-15
95,198
260
2016-01-16
72,692
261
2016-01-17
80,866
262
2016-01-18
126,618
263
2016-01-19
123,059
264
2016-01-20
104,145
265
2016-01-21
138,906
266
2016-01-22
128,393
267
2016-01-23
101,445
268
2016-01-24
117,821
269
2016-01-25
464,123
270
2016-01-26
259,802
271
2016-01-27
155,920
272
NaT
23,853,520
273 rows × 2 columns
In [87]:
df = df.ix[:271]
In [82]:
df
Out[82]:
Day
Users
0
2015-05-01
40,434
1
2015-05-02
26,132
2
2015-05-03
32,169
3
2015-05-04
35,586
4
2015-05-05
35,365
5
2015-05-06
33,851
6
2015-05-07
38,475
7
2015-05-08
54,304
8
2015-05-09
52,073
9
2015-05-10
42,085
10
2015-05-11
46,599
11
2015-05-12
66,755
12
2015-05-13
60,469
13
2015-05-14
45,566
14
2015-05-15
53,777
15
2015-05-16
36,404
16
2015-05-17
34,246
17
2015-05-18
51,926
18
2015-05-19
61,802
19
2015-05-20
64,421
20
2015-05-21
65,658
21
2015-05-22
43,693
22
2015-05-23
37,892
23
2015-05-24
34,667
24
2015-05-25
31,375
25
2015-05-26
48,070
26
2015-05-27
116,569
27
2015-05-28
157,395
28
2015-05-29
59,278
29
2015-05-30
58,530
...
...
...
243
2015-12-30
97,197
244
2015-12-31
78,765
245
2016-01-01
84,231
246
2016-01-02
63,889
247
2016-01-03
54,588
248
2016-01-04
84,144
249
2016-01-05
100,541
250
2016-01-06
232,881
251
2016-01-07
181,296
252
2016-01-08
105,137
253
2016-01-09
82,520
254
2016-01-10
79,769
255
2016-01-11
94,185
256
2016-01-12
112,466
257
2016-01-13
104,724
258
2016-01-14
96,629
259
2016-01-15
95,198
260
2016-01-16
72,692
261
2016-01-17
80,866
262
2016-01-18
126,618
263
2016-01-19
123,059
264
2016-01-20
104,145
265
2016-01-21
138,906
266
2016-01-22
128,393
267
2016-01-23
101,445
268
2016-01-24
117,821
269
2016-01-25
464,123
270
2016-01-26
259,802
271
2016-01-27
155,920
272
NaT
23,853,520
273 rows × 2 columns
In [79]:
df.loc[]
Out[79]:
Day
Users
0
2015-05-01
40,434
1
2015-05-02
26,132
2
2015-05-03
32,169
3
2015-05-04
35,586
4
2015-05-05
35,365
5
2015-05-06
33,851
6
2015-05-07
38,475
7
2015-05-08
54,304
8
2015-05-09
52,073
9
2015-05-10
42,085
10
2015-05-11
46,599
11
2015-05-12
66,755
12
2015-05-13
60,469
13
2015-05-14
45,566
14
2015-05-15
53,777
15
2015-05-16
36,404
16
2015-05-17
34,246
17
2015-05-18
51,926
18
2015-05-19
61,802
19
2015-05-20
64,421
20
2015-05-21
65,658
21
2015-05-22
43,693
22
2015-05-23
37,892
23
2015-05-24
34,667
24
2015-05-25
31,375
25
2015-05-26
48,070
26
2015-05-27
116,569
27
2015-05-28
157,395
28
2015-05-29
59,278
29
2015-05-30
58,530
...
...
...
243
2015-12-30
97,197
244
2015-12-31
78,765
245
2016-01-01
84,231
246
2016-01-02
63,889
247
2016-01-03
54,588
248
2016-01-04
84,144
249
2016-01-05
100,541
250
2016-01-06
232,881
251
2016-01-07
181,296
252
2016-01-08
105,137
253
2016-01-09
82,520
254
2016-01-10
79,769
255
2016-01-11
94,185
256
2016-01-12
112,466
257
2016-01-13
104,724
258
2016-01-14
96,629
259
2016-01-15
95,198
260
2016-01-16
72,692
261
2016-01-17
80,866
262
2016-01-18
126,618
263
2016-01-19
123,059
264
2016-01-20
104,145
265
2016-01-21
138,906
266
2016-01-22
128,393
267
2016-01-23
101,445
268
2016-01-24
117,821
269
2016-01-25
464,123
270
2016-01-26
259,802
271
2016-01-27
155,920
272
NaT
23,853,520
273 rows × 2 columns
In [92]:
pd.read_csv()
Out[92]:
Day
Users
count
272
272
unique
272
272
top
2015-07-19 00:00:00
88,210
freq
1
1
first
2015-05-01 00:00:00
NaN
last
2016-01-27 00:00:00
NaN
In [ ]:
Content source: facemelters/data-science
Similar notebooks: