basic parsing working

03_Sentiment_Analysis.py

@@ -9,14 +9,14 @@ def _():
     import marimo as mo
     import pandas as pd
     from pathlib import Path
+    from utils import create_sentiment_matrix
 
     INPUT_DIR = Path("./data/processing/02_taguette_postprocess")
     WORKING_DIR = Path('./data/processing/03_sentiment_analysis')
 
     if not WORKING_DIR.exists():
         WORKING_DIR.mkdir(parents=True)
-
-    return INPUT_DIR, Path, WORKING_DIR, mo, pd
+    return INPUT_DIR, Path, WORKING_DIR, create_sentiment_matrix, mo, pd
 
 
 @app.cell(hide_code=True)
@@ -62,55 +62,6 @@ def _(mo):
     return
 
 
-@app.cell
-def _(document_name, pd):
-    import numpy as np
-
-    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(f"No sentiment data found for document: {document_name}")
-            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(f"No Voice/Character context found for document: {document_name}")
-            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
-    return (create_sentiment_matrix,)
-
-
 @app.cell(hide_code=True)
 def _(mo):
     mo.md(r"""