学习 · · 146 字 · 约 1 分钟
Pandas DataFrame 速查
Pandas DataFrame 速查
1 DataFrame 初始化
1.1 从列表初始化
data = [['apple', 'fruit', 5], ['bike', 'vehicle', 10], ['computer', 'device', 2]]
dataset = pd.DataFrame(data, columns=['name', 'category', 'number'], dtype=float)
>>> dataset
name category number
0 apple fruit 5.0
1 bike vehicle 10.0
2 computer device 2.0
1.2 从字典初始化
>>> data = {
'name': ['apple', 'bike', 'computer'],
'category': ['fruit', 'vehicle', 'device'],
'number': [5, 10, 2]
}
>>> dataset = pd.DataFrame(data)
>>> dataset
name category number
0 apple fruit 5
1 bike vehicle 10
2 computer device 2
1.3 从文件读取
pandas.read_csv(file_dir, sep: str, usecols: list, na_values: str)
pandas.read_excel(file_dir, sheet_name: int / str / list, usecols: list, na_values: str)
2 DataFrame 操作
2.1 遍历操作
import pandas as pd
data = {
'name': ['apple', 'bike', 'computer'],
'category': ['fruit', 'vehicle', 'device'],
'number': [5, 10, 2]
}
dataset = pd.DataFrame(data)
>>> dataset
name category number
0 apple fruit 5
1 bike vehicle 10
2 computer device 2
for i in range(len(dataset)):
for j in range(len(dataset.columns)):
dataset[dataset.columns[j]][i] = i * len(dataset.columns) + j
print(dataset)
>>> dataset
name category number
0 0 1 2
1 3 4 5
2 6 7 8
2.2 获取指定数据
2.2.1 获取指定元素
获取 “device” 。
>>> dataset
name category number
0 apple fruit 5
1 bike vehicle 10
2 computer device 2
>>> dataset['category'][2]
'device'
# .loc[ , ]
>>> dataset.loc[2, 'category']
'device'
# .iloc[ , ]
>>> dataset.iloc[2, 1]
'device'
2.2.2 获取指定行
获取第2行。
# .loc[ , ]
>>> line_2 = dataset.loc[2, :]
>>> line_2
name computer
category device
number 2
Name: 2, dtype: object
>>> for item in line_2:
... print(item)
...
computer
device
2
# .iloc[ , ]
>>> line_2 = dataset.iloc[2, :]
>>> line_2
name computer
category device
number 2
Name: 2, dtype: object
>>> for item in line_2:
... print(item)
...
computer
device
2
2.2.3 获取指定列
获取 “category” 列。
# .loc[ , ]
>>> row_category = dataset.loc[:, 'category']
>>> row_category
0 fruit
1 vehicle
2 device
Name: category, dtype: object
>>> for item in row_category:
... print(item)
...
fruit
vehicle
device
# .iloc[ , ]
>>> row_category = dataset.iloc[:, 1]
>>> row_category
0 fruit
1 vehicle
2 device
Name: category, dtype: object
>>> for item in row_category:
... print(item)
...
fruit
vehicle
device
2.3 空值判断
df = pd.DataFrame(dict(age=[5, 6, np.NaN],
... born=[pd.NaT, pd.Timestamp('1939-05-27'),
... pd.Timestamp('1940-04-25')],
... name=['Alfred', 'Batman', ''],
... toy=[None, 'Batmobile', 'Joker']))
>>> df
age born name toy
0 5.0 NaT Alfred None
1 6.0 1939-05-27 Batman Batmobile
2 NaN 1940-04-25 Joker
>>> df.isna()
age born name toy
0 False True False True
1 False False False False
2 True False False False
>>> pd.isna(df)
age born name toy
0 False True False True
1 False False False False
2 True False False False
2.4 转array处理
>>> df = pd.DataFrame({'age': [ 3, 29],
... 'height': [94, 170],
... 'weight': [31, 115]})
>>> df
age height weight
0 3 94 31
1 29 170 115
>>> df.values
array([[ 3, 94, 31],
[ 29, 170, 115]], dtype=int64)
2.5 去重
>>> df = pd.DataFrame({
... 'brand': ['Yum Yum', 'Yum Yum', 'Indomie', 'Indomie', 'Indomie'],
... 'style': ['cup', 'cup', 'cup', 'pack', 'pack'],
... 'rating': [4, 4, 3.5, 15, 5]
... })
>>> df
brand style rating
0 Yum Yum cup 4.0
1 Yum Yum cup 4.0
2 Indomie cup 3.5
3 Indomie pack 15.0
4 Indomie pack 5.0
>>> df.drop_duplicates()
brand style rating
0 Yum Yum cup 4.0
2 Indomie cup 3.5
3 Indomie pack 15.0
4 Indomie pack 5.0
>>> df.drop_duplicates(subset=['brand', 'style'], keep='last')
brand style rating
1 Yum Yum cup 4.0
2 Indomie cup 3.5
4 Indomie pack 5.0