pedrofunction

Author: pericotronic

toolkit/data_analysis.py

@@ -54,3 +54,26 @@ def read_csv_zip(zip_file, csv_file, sep=';'):
 
     return df
 
+def chi_squared_test(df, feature, target):
+    import scipy.stats as stats
+    import pandas as pd
+    """
+    This function performs a chi-squared test of independence between two categorical variables.
+
+    Params:
+    - df: A DataFrame containing the variables of interest.
+    - feature: The independent variable to be analyzed.
+    - target: The dependent variable to compare the independent variable with.
+
+    Returns:
+    - chi2: The chi-squared value obtained in the test.
+    - p: The p-value obtained in the test.
+    """
+    # Create a contingency table from the independent and dependent variable data.
+    contingency_table = pd.crosstab(df[feature], df[target])
+
+    # Perform a chi-squared test of independence between the variables.
+    chi2, p, dof, expected = stats.chi2_contingency(contingency_table)
+
+    # Return the chi-squared value and p-value obtained in the test.
+    return chi2, p

toolkit/data_processing.py

@@ -314,3 +314,17 @@ def convert_to_numeric(df,column:str):
     '''
     df[column] = df[column].apply(lambda x: pd.to_numeric(x, errors = 'coerce'))
     return df
+
+def _exponential_smooth(data, alpha):
+    """
+    Function that exponentially smooths dataset so values are less 'rigid'
+    :param alpha: weight factor to weight recent values more
+    """
+
+    smoothed_data = data.ewm(alpha=alpha).mean()
+
+    # Check that the first and last values of the smoothed data are the same as the original data
+    smoothed_data.iloc[0] = data.iloc[0]
+    smoothed_data.iloc[-1] = data.iloc[-1]
+
+    return smoothed_data