Answers for "pandas change status in a column if condition"

pandas update with condition

import pandas as pd
import numpy as np

df = pd.DataFrame({'value':np.arange(1000000)})

# Solution 1 - Fastest :
df['value'] = np.where(df['value'] > 20000, 0, df['value'])

# Solution 2:
df.loc[df['value'] > 20000, 'value'] = 0

# Solution 3:
df['value'] = df['value'].mask(df['value'] > 20000, 0)

# Solution 4 - Slowest, note that df.where applies where condition is wrong:
df['a'] = df.where(df.a <= 20000, 0)

python conditionally create new column in pandas dataframe

# If you only have one condition use numpy.where()
# Example usage with np.where:
df = pd.DataFrame({'Type':list('ABBC'), 'Set':list('ZZXY')}) # Define df
print(df)
  Type Set
0    A   Z
1    B   Z
2    B   X
3    C   Y

# Add new column based on single condition:
df['color'] = np.where(df['Set']=='Z', 'green', 'red')
print(df)
  Type Set  color
0    A   Z  green
1    B   Z  green
2    B   X    red
3    C   Y    red


# If you have multiple conditions use numpy.select()
# Example usage with np.select:
df = pd.DataFrame({'Type':list('ABBC'), 'Set':list('ZZXY')}) # Define df
print(df)
  Type Set
0    A   Z
1    B   Z
2    B   X
3    C   Y

# Set the conditions for determining values in new column:
conditions = [
    (df['Set'] == 'Z') & (df['Type'] == 'A'),
    (df['Set'] == 'Z') & (df['Type'] == 'B'),
    (df['Type'] == 'B')]

# Set the new column values in order of the conditions they should
#	correspond to:
choices = ['yellow', 'blue', 'purple']

# Add new column based on conditions and choices:
df['color'] = np.select(conditions, choices, default='black')

print(df)
# Returns:
  Set Type   color
0   Z    A  yellow
1   Z    B    blue
2   X    B  purple
3   Y    C   black