selenium works; stick to ChromeDriverManager

fingpt/FinGPT-RAG/multisource_retrieval/scrapers/selenium/selenium_app.py

@@ -0,0 +1,18 @@
+from selenium import webdriver
+from selenium.webdriver.chromium.service import ChromiumService
+from webdriver_manager.chrome import ChromeDriverManager
+
+# Set up ChromeOptions
+options = webdriver.ChromeOptions()
+# options.binary_location = "/Users/tianyu/Desktop/Coding/Network/chrome/chrome-mac-arm64"
+
+# Start Chrome using a specific ChromeDriver
+executable_path='/Users/tianyu/Desktop/Coding/Network/chrome/chromedriver-mac-arm64'
+executable_path=ChromeDriverManager().install()
+service=ChromiumService(executable_path=executable_path)
+driver = webdriver.Chrome(service=service, options=options)
+
+# Now you can use the driver object to interact with the browser
+driver.get('https://www.google.com')
+print(driver.title)
+driver.quit()

fingpt/FinGPT-RAG/multisource_retrieval/utils/classification_accuracy_verification.py

@@ -8,7 +8,7 @@ from external_LLMs import external_LLMs
 import pandas as pd
 import openai
 from datasets import load_dataset
-from sklearn.metrics import accuracy_score, f1_score,confusion_matrix
+from sklearn.metrics import accuracy_score, f1_score, recall_score, precision_score
 from tqdm import tqdm
 
 try:
@@ -33,12 +33,15 @@ try:
     df = df.dropna(subset=[actual_classifications_column, predicted_classifications_column])
     df[actual_classifications_column] = df[actual_classifications_column].astype(int)
     df[predicted_classifications_column] = df[predicted_classifications_column].astype(int)
-    computed_f1 = f1_score(df[actual_classifications_column], df[predicted_classifications_column], average='micro')
+    computed_f1 = f1_score(df[actual_classifications_column], df[predicted_classifications_column], average=None)
     computed_accuracy_score = accuracy_score(df[actual_classifications_column], df[predicted_classifications_column])
-
+    computed_precision_score = precision_score(df[actual_classifications_column], df[predicted_classifications_column], average=None)
+    computed_recall_score = recall_score(df[actual_classifications_column], df[predicted_classifications_column], average=None)
 
     print("f1 score: ", computed_f1)
     print("accuracy score: ", computed_accuracy_score)
+    print("precision score: ", computed_precision_score)
+    print("recall score: ", computed_recall_score)
 
 except Exception as e:
     gui.exceptionbox(str(e))

fingpt/FinGPT-RAG/multisource_retrieval/utils/count_contexts.py

@@ -23,23 +23,23 @@ def find_different_rows():
         else:
             gui.msgbox("No rows found without 'http' in 'link' column.")
 
-    # if file_path:
-    #     # Read CSV file using pandas
-    #     df = pd.read_csv(file_path)
-    #
-    #     # Ensure "text" and "contextualized sentences" columns exist
-    #     if "text" not in df.columns or "contextualized_sentence" not in df.columns:
-    #         gui.msgbox("Either or both 'text' and 'contextualized_sentences' columns are missing.")
-    #         return
-    #
-    #     # Find rows where "text" and "contextualized sentences" values are different
-    #     different_rows = df[df['text'] != df['contextualized_sentence']]
-    #
-    #     # Report the different row indexes
-    #     if not different_rows.empty:
-    #         gui.msgbox("total number is {}".format(len(different_rows.index.tolist())))
-    #     else:
-    #         gui.msgbox("No rows found with different values for 'text' and 'contextualized_sentences'.")
+    if file_path:
+        # Read CSV file using pandas
+        df = pd.read_csv(file_path)
+
+        # Ensure "text" and "contextualized sentences" columns exist
+        if "text" not in df.columns or "contextualized_sentence" not in df.columns:
+            gui.msgbox("Either or both 'text' and 'contextualized_sentences' columns are missing.")
+            return
+
+        # Find rows where "text" and "contextualized sentences" values are different
+        different_rows = df[df['text'] != df['contextualized_sentence']]
+
+        # Report the different row indexes
+        if not different_rows.empty:
+            gui.msgbox("total number is {}".format(len(different_rows.index.tolist())))
+        else:
+            gui.msgbox("No rows found with different values for 'text' and 'contextualized_sentences'.")
 
     else:
         gui.msgbox("No file selected.")