from sklearn.datasets import fetch_california_housing
import pandas as pd

# 獲取California Housing數(shù)據(jù)集
data = fetch_california_housing()

# 將數(shù)據(jù)集轉(zhuǎn)換為Pandas DataFrame
df = pd.DataFrame(data.data, columns=data.feature_names)

# 添加目標(biāo)列
df['MedHouseVal'] = data.target

print(data.DESCR)

df.info()

Output >>>


RangeIndex: 20640 entries, 0 to 20639
Data columns (total 9 columns):
 #   Column    Non-Null Count  Dtype  
---  ------    --------------  -----  
 0   MedInc    20640 non-null  float64
 1   HouseAge  20640 non-null  float64
 2   AveRooms  20640 non-null  float64
 3   AveBedrms 20640 non-null  float64
 4   Population   20640 non-null  float64
 5   AveOccup  20640 non-null  float64
 6   Latitude  20640 non-null  float64
 7   Longitude 20640 non-null  float64
 8   MedHouseVal  20640 non-null  float64
dtypes: float64(9)
memory usage: 1.4 MB

df.describe()

# 檢查數(shù)據(jù)幀中的缺失值
missing_values = df.isnull().sum()
print("Missing Values:")
print(missing_values)

Output >>>

Missing Values:
MedInc      0
HouseAge    0
AveRooms    0
AveBedrms   0
Population  0
AveOccup    0
Latitude    0
Longitude   0
MedHouseVal 0
dtype: int64

# 檢查數(shù)據(jù)幀中是否有重復(fù)行
duplicate_rows = df[df.duplicated()]
print("Duplicate Rows:")
print(duplicate_rows)

Output >>>

Duplicate Rows:
Empty DataFrame
Columns: [MedInc, HouseAge, AveRooms, AveBedrms, Population, AveOccup, Latitude, Longitude, MedHouseVal]
Index: []

# 檢查DataFrame中每一列的數(shù)據(jù)類型
data_types = df.dtypes
print("Data Types:")
print(data_types)

Output >>>

Data Types:
MedInc      float64
HouseAge    float64
AveRooms    float64
AveBedrms   float64
Population  float64
AveOccup    float64
Latitude    float64
Longitude   float64
MedHouseVal float64
dtype: object

columns_to_check = ['MedInc', 'AveRooms', 'AveBedrms', 'Population']

# 查找?guī)в挟惓Ｖ档挠涗浀暮瘮?shù)
def find_outliers_pandas(data, column):
 Q1 = data[column].quantile(0.25)
 Q3 = data[column].quantile(0.75)
 IQR = Q3 - Q1
 lower_bound = Q1 - 1.5 * IQR
 upper_bound = Q3 + 1.5 * IQR
 outliers = data[(data[column] < lower_bound) | (data[column] > upper_bound)]
 return outliers

# 對(duì)每個(gè)指定的列查找?guī)в挟惓Ｖ档挠涗?outliers_dict = {}

for column in columns_to-check:
 outliers_dict[column] = find_outliers_pandas(df, column)

# 打印每列中帶有異常值的記錄
for column, outliers in outliers_dict.items():
 print(f"Outliers in '{column}':")
 print(outliers)
 print("\n")

# 檢查'MedInc'列的數(shù)值范圍
valid_range = (0, 16)  
value_range_check = df[~df['MedInc'].between(*valid_range)]
print("Value Range Check (MedInc):")
print(value_range_check)

Output >>>

Value Range Check (MedInc):
Empty DataFrame
Columns: [MedInc, HouseAge, AveRooms, AveBedrms, Population, AveOccup, Latitude, Longitude, MedHouseVal]
Index: []

# AveRooms不應(yīng)小于AveBedrooms
invalid_data = df[df['AveRooms'] < df['AveBedrms']]
print("Invalid Records (AveRooms < AveBedrms):")
print(invalid_data)

Output >>>

Invalid Records (AveRooms < AveBedrms):
Empty DataFrame
Columns: [MedInc, HouseAge, AveRooms, AveBedrms, Population, AveOccup, Latitude, Longitude, MedHouseVal]
Index: []

import pandas as pd
import re

data = {'Date': ['2023-10-29', '2023-11-15', '23-10-2023', '2023/10/29', '2023-10-30']}
df = pd.DataFrame(data)

# 定義預(yù)期的日期格式
date_format_pattern = r'^\d{4}-\d{2}-\d{2}$'  # YYYY-MM-DD format

# 檢查日期值是否符合預(yù)期格式的函數(shù)
def check_date_format(date_str, date_format_pattern):
 return re.match(date_format_pattern, date_str) is not None

# 對(duì)'Date'列應(yīng)用格式檢查
date_format_check = df['Date'].apply(lambda x: check_date_format(x, date_format_pattern))

# 識(shí)別并檢索不符合預(yù)期格式的日期記錄
non_adherent_dates = df[~date_format_check]

if not non_adherent_dates.empty:
 print("Entries that do not follow the expected format:")
 print(non_adherent_dates)
else:
 print("All dates are in the expected format.")

Output >>>

Entries that do not follow the expected format:
      Date
2  23-10-2023
3  2023/10/29