basic parsing working

utils/data_utils.py

@@ -0,0 +1,65 @@
+import pandas as pd
+
+
+def create_sentiment_matrix(doc_df, column_prefix='VT - |CT - ', row_prefix='_V-|_C-'):
+    """
+    Create a sentiment matrix for a specific document.
+
+    Parameters:
+    - df: DataFrame with columns ['document', 'tag', '_context', 'sentiment']
+    - document_name: Name of the document to filter by
+
+    Returns:
+    - DataFrame representing the sentiment matrix
+    """
+
+    # Filter for rows where the tag matches the sentiment prefixes (VT-/CT-)
+    sentiment_rows = doc_df[
+        doc_df['tag'].str.contains(column_prefix, na=False)
+    ].copy()
+
+    if sentiment_rows.empty:
+        print("No sentiment data found")
+        return pd.DataFrame()
+
+    # Filter for rows with valid Voice/Character context
+    valid_rows = sentiment_rows[
+        sentiment_rows['_context'].notna() & 
+        (sentiment_rows['_context'].str.contains(row_prefix, na=False))
+    ].copy()
+
+    if valid_rows.empty:
+        print("No Voice/Character context found")
+        return pd.DataFrame()
+
+    # Create aggregation: group by Voice/Character (_context) and Theme (tag)
+    # Sum sentiment scores for each combination
+    matrix_data = valid_rows.groupby(['_context', 'tag'])['sentiment'].sum().reset_index()
+
+    # Pivot to create the matrix
+    matrix = matrix_data.pivot(index='_context', columns='tag', values='sentiment')
+
+    # # Convert to integers for cleaner display
+    # matrix = matrix.astype(int)
+
+    return matrix
+
+
+
+def extract_theme(tag: str, theme_prefixes='VT - |CT - ') -> str:
+    """
+    Extract the theme from a tag string.
+
+    Parameters:
+    - tag: str, the tag string (e.g., 'VT - Personal Experience')
+    - theme_prefixes: str, prefixes to remove from the tag (e.g., 'VT - |CT - ')
+
+    Returns:
+    - str, the extracted theme (e.g., 'Personal Experience')
+    - None if no theme found
+    """
+    for prefix in theme_prefixes.split('|'):
+        if tag.startswith(prefix):
+            return tag.replace(prefix, '').strip()
+    return None
+