qdesc 0.1.2__py3-none-any.whl → 0.1.4__py3-none-any.whl

qdesc/__init__.py

@@ -0,0 +1,70 @@
+def desc(df):
+    import pandas as pd
+    import numpy as np
+    from scipy.stats import anderson
+    x = np.round(df.describe().T,2)
+    x = x.iloc[:, [0,1,2,5,3,7]]
+    x.rename(columns={'50%': 'median'}, inplace=True)
+    mad_values = {}
+    # computes the manual mad which is more robust to outliers and non-normal distributions
+    for column in df.select_dtypes(include=[np.number]):
+        median = np.median(df[column])
+        abs_deviation = np.abs(df[column] - median)
+        mad = np.median(abs_deviation)
+        mad_values[column] = mad
+    mad_df = pd.DataFrame(list(mad_values.items()), columns=['Variable', 'MAD'])
+    mad_df.set_index('Variable', inplace=True)
+    results = {}
+    # Loop through each column to test only continuous variables (numeric columns)
+    for column in df.select_dtypes(include=[np.number]):  # Only continuous variables
+        result = anderson(df[column])
+        statistic = result.statistic
+        critical_values = result.critical_values
+        # Only select the 5% and 1% significance levels
+        selected_critical_values = {
+            '5% crit_value': critical_values[2],  # 5% critical value
+            '1% crit_value': critical_values[4]   # 1% critical value
+        }
+        # Store the results in a dictionary
+        results[column] = {
+            'AD_stat': statistic,
+            **selected_critical_values  # Add critical values for 5% and 1% levels
+        }
+    # Convert the results dictionary into a DataFrame
+    anderson_df = pd.DataFrame.from_dict(results, orient='index')
+    
+    xl = x.iloc[:, :4]
+    xr = x.iloc[:, 4:]
+    x_df = np.round(pd.concat([xl, mad_df, xr, anderson_df], axis=1),2)
+    return x_df
+
+def freqdist(df, column_name):
+    import pandas as pd
+    if column_name not in df.columns:
+        raise ValueError(f"Column '{column_name}' not found in DataFrame.")
+    
+    if df[column_name].dtype not in ['object', 'category']:
+        raise ValueError(f"Column '{column_name}' is not a categorical column.")
+    
+    freq_dist = df[column_name].value_counts().reset_index()
+    freq_dist.columns = [column_name, 'Count']
+    freq_dist['Percentage'] = (freq_dist['Count'] / len(df)) * 100
+    return freq_dist
+
+
+def freqdist_a(df):
+    results = []  # List to store distributions
+    for column in df.select_dtypes(include=['object', 'category']).columns:
+        frequency_table = df[column].value_counts()
+        percentage_table = df[column].value_counts(normalize=True) * 100
+        distribution = pd.DataFrame({
+            'Column': column,
+            'Value': frequency_table.index,
+            'Count': frequency_table.values,
+            'Percentage': percentage_table.values
+        })
+        results.append(distribution)
+
+    # Combine all distributions into a single DataFrame
+    final_df = pd.concat(results, ignore_index=True)
+    return final_df

{qdesc-0.1.2.dist-info → qdesc-0.1.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: qdesc
-Version: 0.1.2
+Version: 0.1.4
 Summary: Quick and Easy way to do descriptive analysis.
 Author: Paolo Hilado
 Author-email: datasciencepgh@proton.me
@@ -38,6 +38,12 @@ Run the function qd.freqdist(df, "Variable Name") to easily create a frequency d
 * Counts - the number of observations
 * Percentage - percentage of observations from total.
 
+Run the function qd.freqdist_a(df) to easily create frequency distribution tables for all the categorical variables in your data frame. The resulting
+table will include columns such as:
+* Variable levels (i.e., for Satisfaction: Very Low, Low, Moderate, High, Very High) 
+* Counts - the number of observations
+* Percentage - percentage of observations from total.
+
 Later versions will include data visualizations handy for exploring the distribution of the data set.
 
 ## Installation

qdesc-0.1.4.dist-info/RECORD

@@ -0,0 +1,6 @@
+qdesc/__init__.py,sha256=4DVLq35LmNvg5Tq1Mz43h_YIWvS-MbwscbRpuqGKFUY,2933
+qdesc-0.1.4.dist-info/LICENCE.txt,sha256=xdFo-Rt6I7EP7C_qrVeIBIcH_7mRGUh8sciJs2R8VmY,9684
+qdesc-0.1.4.dist-info/METADATA,sha256=MHz5mWEIWOTp47oSPV3BBw_FZX5L4UgGIm1ROYQbRsI,3061
+qdesc-0.1.4.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+qdesc-0.1.4.dist-info/top_level.txt,sha256=JuSs1wWRGN77DVuq-SX-5P7m_mIZF0ikEVgPTBOrHb0,6
+qdesc-0.1.4.dist-info/RECORD,,

qdesc-0.1.4.dist-info/top_level.txt

@@ -0,0 +1 @@
+qdesc

qdesc-0.1.2.dist-info/RECORD

@@ -1,5 +0,0 @@
-qdesc-0.1.2.dist-info/LICENCE.txt,sha256=xdFo-Rt6I7EP7C_qrVeIBIcH_7mRGUh8sciJs2R8VmY,9684
-qdesc-0.1.2.dist-info/METADATA,sha256=ot6kwgtQqyQRmCu9XlkbzEvNIE6eY9wl6BiQMQAccBM,2690
-qdesc-0.1.2.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-qdesc-0.1.2.dist-info/top_level.txt,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
-qdesc-0.1.2.dist-info/RECORD,,

qdesc-0.1.2.dist-info/top_level.txt

@@ -1 +0,0 @@
-