qdesc 0.1.4__py3-none-any.whl → 0.1.6__py3-none-any.whl

qdesc/__init__.py

@@ -52,19 +52,52 @@ def freqdist(df, column_name):
     return freq_dist
 
 
-def freqdist_a(df):
-    results = []  # List to store distributions
+def freqdist_a(df, ascending=False):
+    results = []  
     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
         })
+        distribution = distribution.sort_values(by='Percentage', ascending=ascending)
         results.append(distribution)
-
-    # Combine all distributions into a single DataFrame
     final_df = pd.concat(results, ignore_index=True)
-    return final_df
+    return final_df
+
+def clean_sheet_name(name):
+    # Remove invalid characters
+    name = re.sub(r'[:\\/?*\[\]]', '', name)
+    # Limit to 31 characters
+    name = name.strip()[:31]
+    return name
+
+def freqdist_to_excel(df, output_path, sort_by='Percentage', ascending=False, top_n=None):
+    used_names = set()
+    with pd.ExcelWriter(output_path, engine='xlsxwriter') as writer:
+        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({
+                'Value': frequency_table.index,
+                'Count': frequency_table.values,
+                'Percentage': percentage_table.values
+            })
+            distribution = distribution.sort_values(by=sort_by, ascending=ascending)
+            if top_n is not None:
+                distribution = distribution.head(top_n)
+            # Generate safe sheet name
+            base_name = clean_sheet_name(column)
+            sheet_name = base_name
+            count = 1
+            while sheet_name.lower() in used_names:
+                sheet_name = f"{base_name[:28]}_{count}"  # stay within 31 char limit
+                count += 1
+            used_names.add(sheet_name.lower())
+            distribution.to_excel(writer, sheet_name=sheet_name, index=False)
+    print(f"Frequency distributions written to {output_path}")

{qdesc-0.1.4.dist-info → qdesc-0.1.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: qdesc
-Version: 0.1.4
+Version: 0.1.6
 Summary: Quick and Easy way to do descriptive analysis.
 Author: Paolo Hilado
 Author-email: datasciencepgh@proton.me
@@ -21,6 +21,7 @@ Be sure to run the following prior to using the "qd.desc" function:
 
 The qdesc package provides a quick and easy approach to do descriptive analysis for quantitative data.
 
+## qd.desc Function
 Run the function qd.desc(df) to get the following statistics:
 * count - number of observations
 * mean - measure of central tendency for normal distribution	
@@ -33,17 +34,26 @@ Run the function qd.desc(df) to get the following statistics:
 * 5% crit_value - critical value for a 5% Significance Level	
 * 1% crit_value - critical value for a 1% Significance Level
 
+## qd.freqdist Function
 Run the function qd.freqdist(df, "Variable Name") to easily create a frequency distribution for your chosen categorical variable with the following:
 * Variable Levels (i.e., for Sex Variable: Male and Female)
 * 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:
+## qd.freqdist_a Function
+Run the function qd.freqdist_a(df, ascending = FALSE) to easily create frequency distribution tables, arranged in descending manner (default) or ascending (TRUE), 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.
 
+## qd.freqdist_to_excel Function
+Run the function qd.freqdist_to_excel(df, "Name of file.xlsx", ascending = FALSE ) to easily create frequency distribution tables, arranged in descending manner (default) or ascending (TRUE), for all  the categorical variables in your data frame and SAVED as separate sheets in the .xlsx File. 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-0.1.6.dist-info/RECORD

@@ -0,0 +1,6 @@
+qdesc/__init__.py,sha256=NPRlg4X8wabfKVQ25JbRZLoTEL0f9KwfEPEPLP3I870,4445
+qdesc-0.1.6.dist-info/LICENCE.txt,sha256=xdFo-Rt6I7EP7C_qrVeIBIcH_7mRGUh8sciJs2R8VmY,9684
+qdesc-0.1.6.dist-info/METADATA,sha256=0PQwiWOmpIXzABYsEu52vnnNKgxNH0Fc3Oyc-IaBDy8,3780
+qdesc-0.1.6.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+qdesc-0.1.6.dist-info/top_level.txt,sha256=JuSs1wWRGN77DVuq-SX-5P7m_mIZF0ikEVgPTBOrHb0,6
+qdesc-0.1.6.dist-info/RECORD,,

qdesc-0.1.4.dist-info/RECORD

@@ -1,6 +0,0 @@
-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,,