pandas数据分析

qq_54911309

于 2023-11-28 20:57:54 发布

阅读量153

点赞数

文章标签： pandas 数据分析数据挖掘

本文链接：https://blog.csdn.net/qq_54911309/article/details/134676629

版权

十套练习使用pandas数据分析.6

import pandas as pd
import numpy as np

data = pd.read_table("D:/东华研/数据分析/pandas_exercise/exercise_data/wind.data",sep='\s+',parse_dates=[[0,1,2]])

data.head()

	Yr_Mo_Dy	RPT	VAL	ROS	KIL	SHA	BIR	DUB	CLA	MUL	CLO	BEL	MAL
0	2061-01-01	15.04	14.96	13.17	9.29	NaN	9.87	13.67	10.25	10.83	12.58	18.50	15.04
1	2061-01-02	14.71	NaN	10.83	6.50	12.62	7.67	11.50	10.04	9.79	9.67	17.54	13.83
2	2061-01-03	18.50	16.88	12.33	10.13	11.17	6.17	11.25	NaN	8.50	7.67	12.75	12.71
3	2061-01-04	10.58	6.63	11.75	4.58	4.54	2.88	8.63	1.79	5.83	5.88	5.46	10.88
4	2061-01-05	13.33	13.25	11.42	6.17	10.71	8.21	11.92	6.54	10.92	10.34	12.92	11.83

import datetime
def fix_century(x):
    year = x.year - 100 if x.year > 1989 else x.year
    return datetime.date(year, x.month, x.day)

# apply the function fix_century on the column and replace the values to the right ones
data['Yr_Mo_Dy'] = data['Yr_Mo_Dy'].apply(fix_century)

# data.info()
data.head()

	Yr_Mo_Dy	RPT	VAL	ROS	KIL	SHA	BIR	DUB	CLA	MUL	CLO	BEL	MAL
0	1961-01-01	15.04	14.96	13.17	9.29	NaN	9.87	13.67	10.25	10.83	12.58	18.50	15.04
1	1961-01-02	14.71	NaN	10.83	6.50	12.62	7.67	11.50	10.04	9.79	9.67	17.54	13.83
2	1961-01-03	18.50	16.88	12.33	10.13	11.17	6.17	11.25	NaN	8.50	7.67	12.75	12.71
3	1961-01-04	10.58	6.63	11.75	4.58	4.54	2.88	8.63	1.79	5.83	5.88	5.46	10.88
4	1961-01-05	13.33	13.25	11.42	6.17	10.71	8.21	11.92	6.54	10.92	10.34	12.92	11.83

data["Yr_Mo_Dy"] = pd.to_datetime(data["Yr_Mo_Dy"])
data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 6574 entries, 0 to 6573
Data columns (total 13 columns):
 #   Column    Non-Null Count  Dtype         
---  ------    --------------  -----         
 0   Yr_Mo_Dy  6574 non-null   datetime64[ns]
 1   RPT       6568 non-null   float64       
 2   VAL       6571 non-null   float64       
 3   ROS       6572 non-null   float64       
 4   KIL       6569 non-null   float64       
 5   SHA       6572 non-null   float64       
 6   BIR       6574 non-null   float64       
 7   DUB       6571 non-null   float64       
 8   CLA       6572 non-null   float64       
 9   MUL       6571 non-null   float64       
 10  CLO       6573 non-null   float64       
 11  BEL       6574 non-null   float64       
 12  MAL       6570 non-null   float64       
dtypes: datetime64[ns](1), float64(12)
memory usage: 667.8 KB

data=data.set_index('Yr_Mo_Dy')
data.head()

	RPT	VAL	ROS	KIL	SHA	BIR	DUB	CLA	MUL	CLO	BEL	MAL
Yr_Mo_Dy
1961-01-01	15.04	14.96	13.17	9.29	NaN	9.87	13.67	10.25	10.83	12.58	18.50	15.04
1961-01-02	14.71	NaN	10.83	6.50	12.62	7.67	11.50	10.04	9.79	9.67	17.54	13.83
1961-01-03	18.50	16.88	12.33	10.13	11.17	6.17	11.25	NaN	8.50	7.67	12.75	12.71
1961-01-04	10.58	6.63	11.75	4.58	4.54	2.88	8.63	1.79	5.83	5.88	5.46	10.88
1961-01-05	13.33	13.25	11.42	6.17	10.71	8.21	11.92	6.54	10.92	10.34	12.92	11.83

data.isnull().sum()

RPT    6
VAL    3
ROS    2
KIL    5
SHA    2
BIR    0
DUB    3
CLA    2
MUL    3
CLO    1
BEL    0
MAL    4
dtype: int64

data.shape[0]-data.isnull().sum()

RPT    6568
VAL    6571
ROS    6572
KIL    6569
SHA    6572
BIR    6574
DUB    6571
CLA    6572
MUL    6571
CLO    6573
BEL    6574
MAL    6570
dtype: int64

data.mean().mean()

10.227982360836924

#列求最小值
lco_stars=pd.DataFrame()
lco_stars['min']=data.min()
lco_stars['max']=data.max()
lco_stars['mean']=data.mean()
lco_stars['var']=data.var()
lco_stars

	min	max	mean	var
RPT	0.67	35.80	12.362987	31.566564
VAL	0.21	33.37	10.644314	27.745044
ROS	1.50	33.84	11.660526	25.084571
KIL	0.00	28.46	6.306468	13.001874
SHA	0.13	37.54	10.455834	24.365332
BIR	0.00	26.16	7.092254	15.750446
DUB	0.00	30.37	9.797343	24.776050
CLA	0.00	31.08	8.495053	20.245042
MUL	0.00	25.88	8.493590	17.362826
CLO	0.04	28.21	8.707332	20.285606
BEL	0.13	42.38	13.121007	34.047657
MAL	0.67	42.54	15.599079	44.887233

#行求最小值
lco_stars_1=pd.DataFrame()
lco_stars_1['min']=data.min(axis=1)
lco_stars_1['max']=data.max(axis=1)
lco_stars_1['mean']=data.mean(axis=1)
lco_stars_1['var']=data.var(axis=1)
lco_stars_1.head()

	min	max	mean	var
Yr_Mo_Dy
1961-01-01	9.29	18.50	13.018182	7.889776
1961-01-02	6.50	17.54	11.336364	10.169685
1961-01-03	6.17	18.50	11.641818	13.556476
1961-01-04	1.79	11.75	6.619167	10.228008
1961-01-05	6.17	13.33	10.630000	5.979764

data['date'] = data.index
data.head()

	RPT	VAL	ROS	KIL	SHA	BIR	DUB	CLA	MUL	CLO	BEL	MAL	date
Yr_Mo_Dy
1961-01-01	15.04	14.96	13.17	9.29	NaN	9.87	13.67	10.25	10.83	12.58	18.50	15.04	1961-01-01
1961-01-02	14.71	NaN	10.83	6.50	12.62	7.67	11.50	10.04	9.79	9.67	17.54	13.83	1961-01-02
1961-01-03	18.50	16.88	12.33	10.13	11.17	6.17	11.25	NaN	8.50	7.67	12.75	12.71	1961-01-03
1961-01-04	10.58	6.63	11.75	4.58	4.54	2.88	8.63	1.79	5.83	5.88	5.46	10.88	1961-01-04
1961-01-05	13.33	13.25	11.42	6.17	10.71	8.21	11.92	6.54	10.92	10.34	12.92	11.83	1961-01-05

data[data.index.month==1].mean()

C:\WINDOWS\TEMP/ipykernel_5984/279758014.py:1: FutureWarning: DataFrame.mean and DataFrame.median with numeric_only=None will include datetime64 and datetime64tz columns in a future version.
  data[data.index.month==1].mean()





RPT    14.847325
VAL    12.914560
ROS    13.299624
KIL     7.199498
SHA    11.667734
BIR     8.054839
DUB    11.819355
CLA     9.512047
MUL     9.543208
CLO    10.053566
BEL    14.550520
MAL    18.028763
dtype: float64

data['month'] = data['date'].apply(lambda x: x.month)
data['year'] = data['date'].apply(lambda date: date.year)
data['day'] = data['date'].apply(lambda date: date.day)

january_winds = data.query('month == 1')
january_winds.loc[:,'RPT':'MAL'].mean()

RPT    14.847325
VAL    12.914560
ROS    13.299624
KIL     7.199498
SHA    11.667734
BIR     8.054839
DUB    11.819355
CLA     9.512047
MUL     9.543208
CLO    10.053566
BEL    14.550520
MAL    18.028763
dtype: float64

data

	RPT	VAL	ROS	KIL	SHA	BIR	DUB	CLA	MUL	CLO	BEL	MAL	date	month	year	day
Yr_Mo_Dy
1961-01-01	15.04	14.96	13.17	9.29	NaN	9.87	13.67	10.25	10.83	12.58	18.50	15.04	1961-01-01	1	1961	1
1961-01-02	14.71	NaN	10.83	6.50	12.62	7.67	11.50	10.04	9.79	9.67	17.54	13.83	1961-01-02	1	1961	2
1961-01-03	18.50	16.88	12.33	10.13	11.17	6.17	11.25	NaN	8.50	7.67	12.75	12.71	1961-01-03	1	1961	3
1961-01-04	10.58	6.63	11.75	4.58	4.54	2.88	8.63	1.79	5.83	5.88	5.46	10.88	1961-01-04	1	1961	4
1961-01-05	13.33	13.25	11.42	6.17	10.71	8.21	11.92	6.54	10.92	10.34	12.92	11.83	1961-01-05	1	1961	5
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
1978-12-27	17.58	16.96	17.62	8.08	13.21	11.67	14.46	15.59	14.04	14.00	17.21	40.08	1978-12-27	12	1978	27
1978-12-28	13.21	5.46	13.46	5.00	8.12	9.42	14.33	16.25	15.25	18.05	21.79	41.46	1978-12-28	12	1978	28
1978-12-29	14.00	10.29	14.42	8.71	9.71	10.54	19.17	12.46	14.50	16.42	18.88	29.58	1978-12-29	12	1978	29
1978-12-30	18.50	14.04	21.29	9.13	12.75	9.71	18.08	12.87	12.46	12.12	14.67	28.79	1978-12-30	12	1978	30
1978-12-31	20.33	17.41	27.29	9.59	12.08	10.13	19.25	11.63	11.58	11.38	12.08	22.08	1978-12-31	12	1978	31

6574 rows × 16 columns

data.query('month==1 and day==1')

	RPT	VAL	ROS	KIL	SHA	BIR	DUB	CLA	MUL	CLO	BEL	MAL	date	month	year	day
Yr_Mo_Dy
1961-01-01	15.04	14.96	13.17	9.29	NaN	9.87	13.67	10.25	10.83	12.58	18.50	15.04	1961-01-01	1	1961	1
1962-01-01	9.29	3.42	11.54	3.50	2.21	1.96	10.41	2.79	3.54	5.17	4.38	7.92	1962-01-01	1	1962	1
1963-01-01	15.59	13.62	19.79	8.38	12.25	10.00	23.45	15.71	13.59	14.37	17.58	34.13	1963-01-01	1	1963	1
1964-01-01	25.80	22.13	18.21	13.25	21.29	14.79	14.12	19.58	13.25	16.75	28.96	21.00	1964-01-01	1	1964	1
1965-01-01	9.54	11.92	9.00	4.38	6.08	5.21	10.25	6.08	5.71	8.63	12.04	17.41	1965-01-01	1	1965	1
1966-01-01	22.04	21.50	17.08	12.75	22.17	15.59	21.79	18.12	16.66	17.83	28.33	23.79	1966-01-01	1	1966	1
1967-01-01	6.46	4.46	6.50	3.21	6.67	3.79	11.38	3.83	7.71	9.08	10.67	20.91	1967-01-01	1	1967	1
1968-01-01	30.04	17.88	16.25	16.25	21.79	12.54	18.16	16.62	18.75	17.62	22.25	27.29	1968-01-01	1	1968	1
1969-01-01	6.13	1.63	5.41	1.08	2.54	1.00	8.50	2.42	4.58	6.34	9.17	16.71	1969-01-01	1	1969	1
1970-01-01	9.59	2.96	11.79	3.42	6.13	4.08	9.00	4.46	7.29	3.50	7.33	13.00	1970-01-01	1	1970	1
1971-01-01	3.71	0.79	4.71	0.17	1.42	1.04	4.63	0.75	1.54	1.08	4.21	9.54	1971-01-01	1	1971	1
1972-01-01	9.29	3.63	14.54	4.25	6.75	4.42	13.00	5.33	10.04	8.54	8.71	19.17	1972-01-01	1	1972	1
1973-01-01	16.50	15.92	14.62	7.41	8.29	11.21	13.54	7.79	10.46	10.79	13.37	9.71	1973-01-01	1	1973	1
1974-01-01	23.21	16.54	16.08	9.75	15.83	11.46	9.54	13.54	13.83	16.66	17.21	25.29	1974-01-01	1	1974	1
1975-01-01	14.04	13.54	11.29	5.46	12.58	5.58	8.12	8.96	9.29	5.17	7.71	11.63	1975-01-01	1	1975	1
1976-01-01	18.34	17.67	14.83	8.00	16.62	10.13	13.17	9.04	13.13	5.75	11.38	14.96	1976-01-01	1	1976	1
1977-01-01	20.04	11.92	20.25	9.13	9.29	8.04	10.75	5.88	9.00	9.00	14.88	25.70	1977-01-01	1	1977	1
1978-01-01	8.33	7.12	7.71	3.54	8.50	7.50	14.71	10.00	11.83	10.00	15.09	20.46	1978-01-01	1	1978	1

data.query('day==1')

	RPT	VAL	ROS	KIL	SHA	BIR	DUB	CLA	MUL	CLO	BEL	MAL	date	month	year	day
Yr_Mo_Dy
1961-01-01	15.04	14.96	13.17	9.29	NaN	9.87	13.67	10.25	10.83	12.58	18.50	15.04	1961-01-01	1	1961	1
1961-02-01	14.25	15.12	9.04	5.88	12.08	7.17	10.17	3.63	6.50	5.50	9.17	8.00	1961-02-01	2	1961	1
1961-03-01	12.67	13.13	11.79	6.42	9.79	8.54	10.25	13.29	NaN	12.21	20.62	NaN	1961-03-01	3	1961	1
1961-04-01	8.38	6.34	8.33	6.75	9.33	9.54	11.67	8.21	11.21	6.46	11.96	7.17	1961-04-01	4	1961	1
1961-05-01	15.87	13.88	15.37	9.79	13.46	10.17	9.96	14.04	9.75	9.92	18.63	11.12	1961-05-01	5	1961	1
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
1978-08-01	19.33	15.09	20.17	8.83	12.62	10.41	9.33	12.33	9.50	9.92	15.75	18.00	1978-08-01	8	1978	1
1978-09-01	8.42	6.13	9.87	5.25	3.21	5.71	7.25	3.50	7.33	6.50	7.62	15.96	1978-09-01	9	1978	1
1978-10-01	9.50	6.83	10.50	3.88	6.13	4.58	4.21	6.50	6.38	6.54	10.63	14.09	1978-10-01	10	1978	1
1978-11-01	13.59	16.75	11.25	7.08	11.04	8.33	8.17	11.29	10.75	11.25	23.13	25.00	1978-11-01	11	1978	1
1978-12-01	21.29	16.29	24.04	12.79	18.21	19.29	21.54	17.21	16.71	17.83	17.75	25.70	1978-12-01	12	1978	1