pandas create new column based on condition of other columns code example

Example 1: pandas create new column conditional on other columns

# For creating new column with multiple conditions
conditions = [
    (df['Base Column 1'] == 'A') & (df['Base Column 2'] == 'B'),
    (df['Base Column 3'] == 'C')]
choices = ['Conditional Value 1', 'Conditional Value 2']
df['New Column'] = np.select(conditions, choices, default='Conditional Value 1')

Example 2: add a value to an existing field in pandas dataframe after checking conditions

# Create a new column called based on the value of another column
# np.where assigns True if gapminder.lifeExp>=50 
gapminder['lifeExp_ind'] = np.where(gapminder.lifeExp >= 50, True, False)
gapminder.head(n=3)

Example 3: 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

Example 4: add a value to an existing field in pandas dataframe after checking conditions

gapminder['gdpPercap_ind'] = gapminder.gdpPercap.apply(lambda x: 1 if x >= 1000 else 0)
gapminder.head()