Updated folders and organized the project

Author: basak-tepe

assets/note_taking.csv

@@ -89,7 +89,8 @@ def extract_full_speech(text, speech_no, province, speaker):
 
     for term, years in terms_and_years.items():
         for year in years:
-            folder_path = f"TXTs/d{term}-y{year}_txts/"
+            # Adjust this to your local path
+            folder_path = f"/Volumes/PortableSSD/TPT/TXTs/d{term}-y{year}_txts/"
             for filepath in glob.glob(os.path.join(folder_path, "*.txt")):
                 if filepath.endswith(("fih.txt", "gnd.txt")):
                     continue

build_elasticsearch.md renamed to docs/build_elasticsearch.md

@@ -3,9 +3,9 @@
 from bertopic import BERTopic
 import plotly.express as px
 
-INPUT_FILE = "speeches_clean.csv"
-MODEL_SAVE_PATH = "bertopic_model"
-TOPIC_SUMMARY_FILE = "topic_summary.csv"
+INPUT_FILE = "../data/speeches_clean.csv"
+MODEL_SAVE_PATH = "../bertopic_model"
+TOPIC_SUMMARY_FILE = "../data/topic_summary.csv"
 
 def run_topic_modeling(df: pd.DataFrame):
     print("⚙️  Training BERTopic model (this may take a while)...")

create_elastic.py renamed to scripts/create_elastic.py

@@ -3,7 +3,7 @@
 import plotly.graph_objects as go
 
 # === CONFIG ===
-CSV_FILE = "topic_summary.csv"   # 👈 change to your actual file path
+CSV_FILE = "../data/topic_summary.csv"   # 👈 Updated path for new structure
 
 # === LOAD DATA ===
 df = pd.read_csv(CSV_FILE)