python機器學習與數據分析實戰筆記——pandas

Pandas庫基礎

底層實現是numpy實現的

1.1讀取csv文件

import pandas as pd
food_info=pd.read_csv(r"F:\唐宇迪機器學習資料\機器學習\Python庫代碼（4個）\2-數據分析處理庫pandas\food_info.csv")
print(type(food_info))
#print(food_info.dtypes)
#print(help(pd.read_csv))

<class 'pandas.core.frame.DataFrame'>

其中Shrt_Desc是object類型可以看爲是string類型

其中對應的數據類型如下
object–string
int–int
flota–float
datetime–time value
bool–bool

food_info.head()

	NDB_No	Shrt_Desc	Water_(g)	Energ_Kcal	Protein_(g)	Lipid_Tot_(g)	Ash_(g)	Carbohydrt_(g)	Fiber_TD_(g)	Sugar_Tot_(g)	...	Vit_A_IU	Vit_A_RAE	Vit_E_(mg)	Vit_D_mcg	Vit_D_IU	Vit_K_(mcg)	FA_Sat_(g)	FA_Mono_(g)	FA_Poly_(g)	Cholestrl_(mg)
0	1001	BUTTER WITH SALT	15.87	717	0.85	81.11	2.11	0.06	0.0	0.06	...	2499.0	684.0	2.32	1.5	60.0	7.0	51.368	21.021	3.043	215.0
1	1002	BUTTER WHIPPED WITH SALT	15.87	717	0.85	81.11	2.11	0.06	0.0	0.06	...	2499.0	684.0	2.32	1.5	60.0	7.0	50.489	23.426	3.012	219.0
2	1003	BUTTER OIL ANHYDROUS	0.24	876	0.28	99.48	0.00	0.00	0.0	0.00	...	3069.0	840.0	2.80	1.8	73.0	8.6	61.924	28.732	3.694	256.0
3	1004	CHEESE BLUE	42.41	353	21.40	28.74	5.11	2.34	0.0	0.50	...	721.0	198.0	0.25	0.5	21.0	2.4	18.669	7.778	0.800	75.0
4	1005	CHEESE BRICK	41.11	371	23.24	29.68	3.18	2.79	0.0	0.51	...	1080.0	292.0	0.26	0.5	22.0	2.5	18.764	8.598	0.784	94.0

5 rows × 36 columns

把剛剛讀取的數據部分顯示以下自動顯示前5條數據，如果想顯示前三條，即在括號裏寫3

food_info.head(3)

	NDB_No	Shrt_Desc	Water_(g)	Energ_Kcal	Protein_(g)	Lipid_Tot_(g)	Ash_(g)	Carbohydrt_(g)	Fiber_TD_(g)	Sugar_Tot_(g)	...	Vit_A_IU	Vit_A_RAE	Vit_E_(mg)	Vit_D_mcg	Vit_D_IU	Vit_K_(mcg)	FA_Sat_(g)	FA_Mono_(g)	FA_Poly_(g)	Cholestrl_(mg)
0	1001	BUTTER WITH SALT	15.87	717	0.85	81.11	2.11	0.06	0.0	0.06	...	2499.0	684.0	2.32	1.5	60.0	7.0	51.368	21.021	3.043	215.0
1	1002	BUTTER WHIPPED WITH SALT	15.87	717	0.85	81.11	2.11	0.06	0.0	0.06	...	2499.0	684.0	2.32	1.5	60.0	7.0	50.489	23.426	3.012	219.0
2	1003	BUTTER OIL ANHYDROUS	0.24	876	0.28	99.48	0.00	0.00	0.0	0.00	...	3069.0	840.0	2.80	1.8	73.0	8.6	61.924	28.732	3.694	256.0

3 rows × 36 columns

想要輸入末尾幾行則用food_info.tail()

food_info.tail(4)

	NDB_No	Shrt_Desc	Water_(g)	Energ_Kcal	Protein_(g)	Lipid_Tot_(g)	Ash_(g)	Carbohydrt_(g)	Fiber_TD_(g)	Sugar_Tot_(g)	...	Vit_A_IU	Vit_A_RAE	Vit_E_(mg)	Vit_D_mcg	Vit_D_IU	Vit_K_(mcg)	FA_Sat_(g)	FA_Mono_(g)	FA_Poly_(g)	Cholestrl_(mg)
8614	90240	SCALLOP (BAY&SEA) CKD STMD	70.25	111	20.54	0.84	2.97	5.41	0.0	0.0	...	5.0	2.0	0.0	0.0	2.0	0.0	0.218	0.082	0.222	41.0
8615	90480	SYRUP CANE	26.00	269	0.00	0.00	0.86	73.14	0.0	73.2	...	0.0	0.0	0.0	0.0	0.0	0.0	0.000	0.000	0.000	0.0
8616	90560	SNAIL RAW	79.20	90	16.10	1.40	1.30	2.00	0.0	0.0	...	100.0	30.0	5.0	0.0	0.0	0.1	0.361	0.259	0.252	50.0
8617	93600	TURTLE GREEN RAW	78.50	89	19.80	0.50	1.20	0.00	0.0	0.0	...	100.0	30.0	0.5	0.0	0.0	0.1	0.127	0.088	0.170	50.0

4 rows × 36 columns

food_info.columns#輸出列名

Index(['NDB_No', 'Shrt_Desc', 'Water_(g)', 'Energ_Kcal', 'Protein_(g)',
       'Lipid_Tot_(g)', 'Ash_(g)', 'Carbohydrt_(g)', 'Fiber_TD_(g)',
       'Sugar_Tot_(g)', 'Calcium_(mg)', 'Iron_(mg)', 'Magnesium_(mg)',
       'Phosphorus_(mg)', 'Potassium_(mg)', 'Sodium_(mg)', 'Zinc_(mg)',
       'Copper_(mg)', 'Manganese_(mg)', 'Selenium_(mcg)', 'Vit_C_(mg)',
       'Thiamin_(mg)', 'Riboflavin_(mg)', 'Niacin_(mg)', 'Vit_B6_(mg)',
       'Vit_B12_(mcg)', 'Vit_A_IU', 'Vit_A_RAE', 'Vit_E_(mg)', 'Vit_D_mcg',
       'Vit_D_IU', 'Vit_K_(mcg)', 'FA_Sat_(g)', 'FA_Mono_(g)', 'FA_Poly_(g)',
       'Cholestrl_(mg)'],
      dtype='object')

food_info.shape#輸出維度

(8618, 36)

1.2運用切片取數據

food_info.loc[3:6]#與列表等切片用法一致

	NDB_No	Shrt_Desc	Water_(g)	Energ_Kcal	Protein_(g)	Lipid_Tot_(g)	Ash_(g)	Carbohydrt_(g)	Fiber_TD_(g)	Sugar_Tot_(g)	...	Vit_A_IU	Vit_A_RAE	Vit_E_(mg)	Vit_D_mcg	Vit_D_IU	Vit_K_(mcg)	FA_Sat_(g)	FA_Mono_(g)	FA_Poly_(g)	Cholestrl_(mg)
3	1004	CHEESE BLUE	42.41	353	21.40	28.74	5.11	2.34	0.0	0.50	...	721.0	198.0	0.25	0.5	21.0	2.4	18.669	7.778	0.800	75.0
4	1005	CHEESE BRICK	41.11	371	23.24	29.68	3.18	2.79	0.0	0.51	...	1080.0	292.0	0.26	0.5	22.0	2.5	18.764	8.598	0.784	94.0
5	1006	CHEESE BRIE	48.42	334	20.75	27.68	2.70	0.45	0.0	0.45	...	592.0	174.0	0.24	0.5	20.0	2.3	17.410	8.013	0.826	100.0
6	1007	CHEESE CAMEMBERT	51.80	300	19.80	24.26	3.68	0.46	0.0	0.46	...	820.0	241.0	0.21	0.4	18.0	2.0	15.259	7.023	0.724	72.0

4 rows × 36 columns

現在要用列名來取數據，第一行爲列名

ndb=food_info['NDB_No']
print(ndb)

0        1001
1        1002
2        1003
3        1004
4        1005
        ...  
8613    83110
8614    90240
8615    90480
8616    90560
8617    93600
Name: NDB_No, Length: 8618, dtype: int64

如果想要取多個列將這些列表組成一個list傳入即可

1.3進行數學運算

print(food_info["Iron_(mg)"])
div_1000=food_info["Iron_(mg)"]/1000
print(div_1000)#進行對應的每個元素操作

0       0.02
1       0.16
2       0.00
3       0.31
4       0.43
        ... 
8613    1.40
8614    0.58
8615    3.60
8616    3.50
8617    1.40
Name: Iron_(mg), Length: 8618, dtype: float64
0       0.00002
1       0.00016
2       0.00000
3       0.00031
4       0.00043
         ...   
8613    0.00140
8614    0.00058
8615    0.00360
8616    0.00350
8617    0.00140
Name: Iron_(mg), Length: 8618, dtype: float64

water_energy=food_info["Water_(g)"]*food_info["Energ_Kcal"]
#對應的列與列進行運算
iron_grams=food_info["Iron_(mg)"]/1000
print(food_info.shape)
food_info["Iron_(g)"]=iron_grams#新加一列
print(food_info.shape)

(8618, 36)
(8618, 37)

對特定的列求最值.max(),.mean(),.min()

import pandas as pd
titanic_train=pd.read_csv(r'F:\唐宇迪機器學習資料\機器學習\Python庫代碼（4個）\2-數據分析處理庫pandas\titanic_train.csv')
age=titanic_train["Age"]
print(age)

0      22.0
1      38.0
2      26.0
3      35.0
4      35.0
       ... 
886    27.0
887    19.0
888     NaN
889    26.0
890    32.0
Name: Age, Length: 891, dtype: float64

print(pd.isnull(age))#判斷是否爲缺失值
len(pd.isnull(age))

0      False
1      False
2      False
3      False
4      False
       ...  
886    False
887    False
888     True
889    False
890    False
Name: Age, Length: 891, dtype: bool





891

#這裏得True與flase可以當一個索引
titanic_train['Age'].mean()#這裏默認情況下是不計算nan值得

29.69911764705882

分組求和/分類別求和

import numpy as np
titanic_survival=titanic_train["Survived"]
#算每個類別對應得平均人數
passenger_survival=titanic_train.pivot_table(index='Pclass',values="Survived",aggfunc=np.mean)
print(passenger_survival)
#aggfunc不設置默認是求均值

        Survived
Pclass          
1       0.629630
2       0.472826
3       0.242363

對於每一個Pclass對應得有獲救率

port_stats=titanic_train.pivot_table(index="Embarked",values=['Fare','Survived'],aggfunc=[np.sum])
print(port_stats)#可以進行分組求和求均值等等

                 sum         
                Fare Survived
Embarked                     
C         10072.2962       93
Q          1022.2543       30
S         17439.3988      217

#去除缺失值得行或列
drop_na_colnums=titanic_train.dropna(axis=1)
print(drop_na_colnums.shape)

(891, 9)