การลบค่าที่หายไป

import pandas as pd
import numpy as np

# Example: randomly missing salary data (MCAR-like)
df = pd.DataFrame({
    'name': ['Alice', 'Bob', 'Carol', 'Dave'],
    'salary': [50000, np.nan, 70000, np.nan]
})
print('Before drop:', df.shape)  # (4, 2)
print(df)

import pandas as pd
import numpy as np

df = pd.DataFrame({
    'a': [1, np.nan, 3, np.nan],
    'b': [10, 20, np.nan, 40],
    'c': [100, 200, 300, 400]
})

cleaned = df.dropna()
print(cleaned)
#      a     b    c
# 0  1.0  10.0  100

print('Original shape:', df.shape)    # (4, 3)
print('Cleaned shape:', cleaned.shape) # (1, 3)

import pandas as pd
import numpy as np

df = pd.DataFrame({
    'a': [1, np.nan, np.nan],
    'b': [2, np.nan, np.nan],
    'c': [3, 4, np.nan]
})

# Row 2 has ALL NaN — dropped
# Row 1 has partial NaN — kept with how='all'
cleaned = df.dropna(how='all')
print(cleaned)
#      a    b    c
# 0  1.0  2.0  3.0
# 1  NaN  NaN  4.0

import pandas as pd
import numpy as np

df = pd.DataFrame({
    'user_id': [1, np.nan, 3],
    'score': [88, 95, np.nan],
    'notes': ['ok', 'good', np.nan]
})

# Drop row only if user_id is missing — score and notes NaN are ok
cleaned = df.dropna(subset=['user_id'])
print(cleaned)
#    user_id  score notes
# 0      1.0   88.0    ok
# 2      3.0    NaN   NaN

import pandas as pd
import numpy as np

df = pd.DataFrame({
    'a': [1, np.nan, np.nan],
    'b': [2, 3, np.nan],
    'c': [4, np.nan, np.nan],
    'd': [5, 6, np.nan]
})

# Keep rows with at least 3 non-null values
cleaned = df.dropna(thresh=3)
print(cleaned)
#      a    b    c    d
# 0  1.0  2.0  4.0  5.0
# 1  NaN  3.0  NaN  6.0

import pandas as pd
import numpy as np

df = pd.DataFrame({
    'id': [1, 2, 3],
    'name': ['A', 'B', 'C'],
    'temp': [np.nan, np.nan, np.nan],  # completely empty column
    'score': [80, 90, 85]
})

# Drop columns that have any NaN
cleaned = df.dropna(axis=1)
print(cleaned)
#    id name  score
# 0   1    A     80
# 1   2    B     90
# 2   3    C     85

import pandas as pd
import numpy as np

df = pd.DataFrame({
    'a': [1, 2, np.nan, 4, 5],
    'b': [np.nan, np.nan, np.nan, np.nan, 5],  # 80% missing
    'c': [1, np.nan, 3, 4, 5]                   # 20% missing
})

threshold = 0.5
high_missing = df.columns[df.isna().mean() > threshold]
print('Dropping:', high_missing.tolist())  # ['b']

cleaned = df.drop(columns=high_missing)
print(cleaned)

import pandas as pd
import numpy as np

df = pd.DataFrame({
    'val': [1, np.nan, 3, np.nan, 5]
})

cleaned = df.dropna()
print('With original index:')
print(cleaned)  # indices 0, 2, 4

cleaned_reset = cleaned.reset_index(drop=True)
print('With reset index:')
print(cleaned_reset)  # indices 0, 1, 2

import pandas as pd
import numpy as np

df = pd.DataFrame({
    'region': ['East', 'West', None, 'East'],
    'revenue': [100, np.nan, 300, 400]
})

result = (
    df
    .dropna(subset=['region', 'revenue'])
    .groupby('region')['revenue'].sum()
)
print(result)
# region
# East    500.0
# dtype: float64

import pandas as pd
import numpy as np

df = pd.DataFrame({
    'user': ['Alice', 'Bob', 'Carol', 'Dave'],
    'age': [25, np.nan, 30, np.nan]
})

missing_pct = df['age'].isna().mean()
print(f'Missing age: {missing_pct:.0%}')  # 50%
# 50% missing is high — consider imputing instead of dropping
# df['age'].fillna(df['age'].median(), inplace=True)

import pandas as pd
import numpy as np

df = pd.DataFrame({
    'id': [1, 2, 3, np.nan],
    'feature': [1.0, np.nan, 3.0, 4.0],
    'useless': [np.nan, np.nan, np.nan, np.nan]
})

clean = (
    df
    .dropna(how='all')              # remove all-NaN rows
    .drop(columns=df.columns[df.isna().mean() > 0.9])  # remove >90% empty cols
    .dropna(subset=['id'])           # must have an ID
)
print(clean)
#      id  feature
# 0   1.0      1.0
# 1   2.0      NaN
# 2   3.0      3.0