import pandas as pd

# 创建示例DataFrame
df = pd.DataFrame({
    'A': ['apple', 'banana', 'apple', 'orange', 'banana'],
    'B': [1, 2, 1, 3, 2],
    'C': ['red', 'yellow', 'red', 'orange', 'yellow']
})

# 统计单列
count_A = df['A'].value_counts()
print(count_A)

apple     2
banana    2
orange    1
Name: A, dtype: int64

# 统计所有列
for column in df.columns:
    print(f"Column {column} value counts:")
    print(df[column].value_counts())
    print()

# 包含缺失值
print(df['A'].value_counts(dropna=False))

# 按值排序而非计数
print(df['A'].value_counts(ascending=True))

# 显示相对频率
print(df['A'].value_counts(normalize=True))

# 使用groupby统计
print(df.groupby('A').size())

# 统计多列组合的出现次数
print(df.groupby(['A', 'B']).size())

df['A'].value_counts(dropna=False)

df['A'].value_counts(normalize=True)

pd.crosstab(df['A'], df['B'])

count_dict = df['A'].value_counts().to_dict()
print(count_dict)

df['A_count'] = df['A'].map(df['A'].value_counts())
print(df)

unique_counts = df.nunique()
print(unique_counts)