長寬表轉換¶

使用flights資料集來說明Long Form跟Wide Form。

https://github.com/mwaskom/seaborn-data/raw/master/flights.csv

In [ ]:

import pandas as pd
import plotly.express as px

import pandas as pd import plotly.express as px

In [ ]:

url = "https://github.com/mwaskom/seaborn-data/raw/master/flights.csv"

url = "https://github.com/mwaskom/seaborn-data/raw/master/flights.csv"

In [ ]:

df = pd.read_csv(url)

df = pd.read_csv(url)

In [ ]:

df

df

Out[ ]:

	year	month	passengers
0	1949	January	112
1	1949	February	118
2	1949	March	132
3	1949	April	129
4	1949	May	121
...	...	...	...
139	1960	August	606
140	1960	September	508
141	1960	October	461
142	1960	November	390
143	1960	December	432

144 rows × 3 columns

使用pivot將long form的資料轉成wide form的資料¶

In [ ]:

wide = df.pivot(index='year',columns='month',values='passengers')

wide = df.pivot(index='year',columns='month',values='passengers')

In [ ]:

wide

wide

Out[ ]:

month	April	August	December	February	January	July	June	March	May	November	October	September
year
1949	129	148	118	118	112	148	135	132	121	104	119	136
1950	135	170	140	126	115	170	149	141	125	114	133	158
1951	163	199	166	150	145	199	178	178	172	146	162	184
1952	181	242	194	180	171	230	218	193	183	172	191	209
1953	235	272	201	196	196	264	243	236	229	180	211	237
1954	227	293	229	188	204	302	264	235	234	203	229	259
1955	269	347	278	233	242	364	315	267	270	237	274	312
1956	313	405	306	277	284	413	374	317	318	271	306	355
1957	348	467	336	301	315	465	422	356	355	305	347	404
1958	348	505	337	318	340	491	435	362	363	310	359	404
1959	396	559	405	342	360	548	472	406	420	362	407	463
1960	461	606	432	391	417	622	535	419	472	390	461	508

In [ ]:

px.imshow(wide, title='旅客人數')

px.imshow(wide, title='旅客人數')

In [ ]:

px.imshow(wide, text_auto=True, title='旅客人數')

px.imshow(wide, text_auto=True, title='旅客人數')

使用melt將wide form的資料轉成long form的資料¶

In [ ]:

df.melt?

df.melt?

In [ ]:

long = wide.reset_index().melt('year', var_name='month', value_name='passengers')

long = wide.reset_index().melt('year', var_name='month', value_name='passengers')

In [ ]:

long

long

Out[ ]:

	year	month	passengers
0	1949	April	129
1	1950	April	135
2	1951	April	163
3	1952	April	181
4	1953	April	235
...	...	...	...
139	1956	September	355
140	1957	September	404
141	1958	September	404
142	1959	September	463
143	1960	September	508

144 rows × 3 columns

In [ ]: