Update test.py

test.py

@@ -3,31 +3,35 @@ import re
 
 import pandas as pd
 
-# Assuming you have a DataFrame named merge_data
-# Example:
-# merge_data = pd.read_csv('your_data.csv')  # load your data
-
-# List of columns to compare (adjust based on your actual DataFrame)
-columns_to_compare = [
-    "Biomarker Name Source", "Biomarker Test Type", "Biomarker Test Result Source", 
-    "Protein Alteration (p Notation Source)", "DNA Alteration (c notation Source)", 
-    "Biomarker Variant Type", "Biomarker Test Result", "Protein Alteration (p Notation Source)", 
-    "DNA Alteration (c notation Source)"
-]
-
-# Calculate differences
-differences = {}
-
-for col in columns_to_compare:
-    data_col = f"{col}_data"
-    gt_col = f"{col}_gt"
-    differences[f"{col}_diff"] = merge_data[data_col] != merge_data[gt_col]
-
-# Create a DataFrame to show differences
-diff_df = pd.DataFrame(differences)
-
-# Show the resulting differences
-diff_df
+# Load your data (replace 'your_file.csv' with the actual file path)
+merge_data = pd.read_csv('your_file.csv')
+
+# Calculate value counts for columns ending with _data and _gt
+columns_data = [col for col in merge_data.columns if col.endswith('_data')]
+columns_gt = [col for col in merge_data.columns if col.endswith('_gt')]
+
+# Initialize a dictionary to store value counts and differences
+value_counts_diff = {}
+
+for data_col, gt_col in zip(columns_data, columns_gt):
+    data_counts = merge_data[data_col].value_counts(dropna=False)
+    gt_counts = merge_data[gt_col].value_counts(dropna=False)
+    
+    # Create a DataFrame combining the counts
+    combined_counts = pd.DataFrame({
+        'data_counts': data_counts,
+        'gt_counts': gt_counts
+    }).fillna(0)
+    
+    # Calculate the difference between data and gt counts
+    combined_counts['difference'] = combined_counts['data_counts'] - combined_counts['gt_counts']
+    
+    # Store in dictionary
+    value_counts_diff[data_col] = combined_counts
+
+# Display the results for each column
+value_counts_diff
+