Update app.py

app.py

@@ -1,60 +1,60 @@
 import streamlit as st
 import pandas as pd
-from transformers import AutoTokenizer, AutoModelForTableQuestionAnswering
-import datetime
-import requests
-
-class InterestCalculatorApp:
-    def __init__(self):
-        self.invoices_df = pd.DataFrame()
-        self.base_rates_df = pd.DataFrame()
-        self.late_payment_interest = st.sidebar.slider("Late Payment Interest Rate (%)", min_value=0.0, max_value=10.0, value=4.0)
-        self.compounding_method = st.sidebar.selectbox(
-            "Compounding Method", [
-                "x% above Base Rate (daily)",
-                "x% above Base Rate (annually)",
-                "Quarterly compounding (25 Mar, 24 Jun, 29 Sep, 25 Dec)",
-                "Quarterly compounding (1 Mar, 1 Jun, 1 Sep, 1 Dec)"
-            ]
-        )
-        self.tokenizer = AutoTokenizer.from_pretrained("google/tapas-large-finetuned-wtq")
-        self.model = AutoModelForTableQuestionAnswering.from_pretrained("google/tapas-large-finetuned-wtq")
-
-    def load_invoices(self, file_path):
-        try:
-            self.invoices_df = pd.read_excel(file_path, parse_dates=True)
-            self.invoices_df = self.invoices_df.fillna('N/A')  # Handle missing values
-            self.invoices_df = self.invoices_df.applymap(lambda x: str(x).strip() if isinstance(x, str) else str(x))
-            st.success("Invoices loaded successfully.")
-        except Exception as e:
-            st.error(f"Failed to load invoices: {e}")
-
-    def ask_tapas(self, query, table):
-        if not isinstance(table, pd.DataFrame):
-            raise TypeError("Expected the table to be a pd.DataFrame, got {}".format(type(table).__name__))
-
-        table = table.applymap(lambda x: str(x) if not pd.isnull(x) else "N/A")
-        inputs = self.tokenizer(table=table, queries=[query], return_tensors="pt", padding=True)
-        outputs = self.model(**inputs)
-        predicted_answer = self.tokenizer.decode(outputs.logits.argmax(dim=-1))
-        return predicted_answer
-
-    def main(self):
-        st.title("Interest Calculation App")
-        file_path = st.file_uploader("Upload Invoices File", type=["xlsx"])
-        if file_path is not None:
-            self.load_invoices(file_path)
-
-        query = st.text_input("Enter your query:")
-        if query:
-            if not self.invoices_df.empty:
-                st.write("Invoice Data:")
-                st.dataframe(self.invoices_df)
-                answer = self.ask_tapas(query, self.invoices_df)
-                st.write("Answer:", answer)
-            else:
-                st.warning("Please upload the invoices file first.")
+import openai
+
+# Function to calculate late interest
+def calculate_late_interest(data, late_interest_rate):
+    # Check if 'due_date' and 'payment_date' columns exist
+    if 'due_date' not in data.columns or 'payment_date' not in data.columns:
+        st.error("Error: 'due_date' or 'payment_date' columns not found in the uploaded file.")
+        return None
+
+    # Convert 'due_date' and 'payment_date' to datetime
+    data['due_date'] = pd.to_datetime(data['due_date'], errors='coerce')
+    data['payment_date'] = pd.to_datetime(data['payment_date'], errors='coerce')
+
+    # Calculate late days and late interest
+    data['late_days'] = (data['payment_date'] - data['due_date']).dt.days.clip(lower=0)
+    data['late_interest'] = data['late_days'] * data['amount'] * (late_interest_rate / 100)
+    return data
+
+# Streamlit App
+def main():
+    st.title("Invoice Interest Calculator and Conversation")
+
+    # Allow user to upload Excel sheet
+    uploaded_file = st.file_uploader("Upload Excel file", type=["xlsx", "xls"])
+
+    if uploaded_file is not None:
+        df = pd.read_excel(uploaded_file)
+
+        # Display uploaded data
+        st.write("Uploaded Data:")
+        st.write(df)
+
+        # Allow user to specify late interest rate
+        late_interest_rate = st.number_input("Enter Late Interest Rate (%):", min_value=0.0, max_value=100.0, step=0.1)
+
+        # Analyze data and calculate late interest
+        df_with_interest = calculate_late_interest(df, late_interest_rate)
+
+        if df_with_interest is not None:
+            # Display analyzed data
+            st.write("Data with Late Interest Calculated:")
+            st.write(df_with_interest)
+
+            # Allow user to engage in conversation
+            user_input = st.text_input("Start a conversation:")
+            if st.button("Send"):
+                openai.api_key = api_key  # Set OpenAI API key
+                completion = openai.Completion.create(
+                    engine="davinci-codex",
+                    prompt=user_input,
+                    max_tokens=100
+                )
+                response = completion.choices[0].text.strip()
+                st.write("AI's Response:")
+                st.write(response)
 
 if __name__ == "__main__":
-    app = InterestCalculatorApp()
-    app.main()  # Corrected call
+    main()