Created
May 18, 2020 11:40
-
-
Save pierrelouisbescond/ea21612fee7d809069befd5d91e3da45 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
def generate_min_max_population(df, constraints, generation_size): | |
# The names, min-max and number of features are extracted from the DataFrame | |
features_nb = df.shape[1] | |
features_names = df.columns | |
df_min_max = df.describe().loc[["min","max"],:] | |
# We initialize the new population DataFrame with zeros | |
new_population = pd.DataFrame(np.zeros((generation_size,features_nb)), columns=features_names) | |
# For each feature, we create a randomized array with a uniform distribution | |
# between the observed min and max of the feature, except for the constrained | |
# ones where the value is unique | |
for column_name in features_names: | |
if column_name in constraints.index: | |
new_population[column_name] = np.ones(generation_size)*constraints["constrained_feature_value"].loc[column_name] | |
else: | |
new_population[column_name] = np.random.uniform(df_min_max.loc["min",column_name], df_min_max.loc["max",column_name], generation_size) | |
return new_population |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment