Update app.py

app.py

@@ -11,6 +11,9 @@ from sklearn.cluster import KMeans
 from sklearn.decomposition import PCA
 import json
 import math
+from transformers import pipeline
+
+classifier = pipeline('zero-shot-classification', model='MoritzLaurer/deberta-v3-large-zeroshot-v1.1-all-33')
 
 def sorting(df):
     df.index = list(map(float, df.index))
@@ -539,6 +542,19 @@ def sample_size_calculator(confidence_level, p, E):
     
     return n
 
+import pandas as pd
+
+def categorize_sentences(prompt, df, Text_name):
+    texts = df[Text_name].tolist()
+
+    labels = []
+    for text in texts:
+        result = classifier(text, candidate_labels=[prompt])
+        labels.append(result['labels'][0])
+
+    df['labels'] = labels
+    return df
+
 def upload_and_select_dataframe():
     st.sidebar.title("File Upload")
     uploaded_files = st.sidebar.file_uploader("Choose CSV or Excel files", type=["csv", "xlsx", "xls", "xlsb"], accept_multiple_files=True)
@@ -581,7 +597,6 @@ df = upload_and_select_dataframe()
 
 try:
     try:
-        d = df.head()
         st.subheader("Data preview")
         st.dataframe(df.head())
 
@@ -925,27 +940,19 @@ try:
                     st.success("Z-Test analysis completed successfully.")
 
     elif main_option == "Coding":
-        """
         selected_list = st.sidebar.multiselect(
             'Select the desired "Open Question" column.', 
             cols,
             default=[]
         )
         df["id"] = df.index
-        api_key = "sk-e2a7f307b1ad4c649f9fa1f6ebd582e8"
         prompt_user = st.text_input("Write a brief description of the selected column question.")
         if st.button("Submit"):
 
-            df2 = categorize_responses_persian(initial_prompt = prompt_user, 
-                        dataframe = df[["id"]+selected_list],
-                        id_column = "id",
-                        text_column = selected_list[0],
-                        api_key = api_key)
+            df2 = categorize_sentences(prompt_user, df, selected_list)
             
             st.subheader("Categorized data")
             st.dataframe(df2)
-            """
-        st.info("This section of the program is under development.")
         
     elif main_option == "Machine Learning":
         st.info("This section of the program is under development.")