Update app.py

app.py

@@ -15,79 +15,82 @@ st.markdown("""
 """, unsafe_allow_html=True)
 
 # File upload interface
-uploaded_file = st.file_uploader("Upload a CSV or XLSX file", type=['csv', 'xlsx'])
+uploaded_file = st.file_uploader("carregue um arquivo CSV ou XLSX", type=['csv', 'xlsx'])
 
 if uploaded_file:
-    # Load the file into a DataFrame
-    if uploaded_file.name.endswith('.csv'):
-        df = pd.read_csv(uploaded_file, quotechar='"', encoding='utf-8')
-    elif uploaded_file.name.endswith('.xlsx'):
-        df = pd.read_excel(uploaded_file)
-
-    # Data preprocessing for Prophet
-    new_df = df.iloc[2:, 9:-1].fillna(0)
-    new_df.columns = df.iloc[1, 9:-1]
-    new_df.columns = new_df.columns.str.replace(r" \(\d+\)", "", regex=True)
-
-    month_dict = {
-        'Jan': '01', 'Fev': '02', 'Mar': '03', 'Abr': '04',
-        'Mai': '05', 'Jun': '06', 'Jul': '07', 'Ago': '08',
-        'Set': '09', 'Out': '10', 'Nov': '11', 'Dez': '12'
-    }
-
-    def convert_column_name(column_name):
-        if column_name == 'Rótulos de Linha':
-            return column_name
-        parts = column_name.split('/')
-        month = parts[0].strip()
-        year = parts[1].strip()
-        year = ''.join(filter(str.isdigit, year))
-        month_number = month_dict.get(month, '00')
-        return f"{month_number}/{year}"
-
-    new_df.columns = [convert_column_name(col) for col in new_df.columns]
-    new_df.columns = pd.to_datetime(new_df.columns, errors='coerce')
-    new_df.rename(columns={new_df.columns[0]: 'Rotulo'}, inplace=True)
-    df_clean = new_df.copy()
-
-    # Create an empty DataFrame to store all anomalies
-    all_anomalies = pd.DataFrame()
-
-    # Process each row in the DataFrame
-    for index, row in df_clean.iterrows():
-        data = pd.DataFrame({
-            'ds': [col for col in df_clean.columns if isinstance(col, pd.Timestamp)],
-            'y': row[[isinstance(col, pd.Timestamp) for col in df_clean.columns]].values
-        })
-
-        data = data[data['y'] > 0].reset_index(drop=True)
-        if data.empty or len(data) < 2:
-            print(f"Skipping group {row['Rotulo']} because there are less than 2 non-zero observations.")
-            continue
-
-        try:
-            model = Prophet(interval_width=0.95)
-            model.fit(data)
-        except ValueError as e:
-            print(f"Skipping group {row['Rotulo']} due to error: {e}")
-            continue
-
-        future = model.make_future_dataframe(periods=12, freq='M')
-        forecast = model.predict(future)
-
-        num_real = len(data)
-        num_forecast = len(forecast)
-        real_values = list(data['y']) + [None] * (num_forecast - num_real)
-        forecast['real'] = real_values
-        anomalies = forecast[(forecast['real'] < forecast['yhat_lower']) | (forecast['real'] > forecast['yhat_upper'])]
-
-        anomalies['Group'] = row['Rotulo']
-        all_anomalies = pd.concat([all_anomalies, anomalies[['ds', 'real', 'Group']]], ignore_index=True)
-
-    # Preparing anomalies DataFrame for TAPEX model
-    all_anomalies.rename(columns={"ds": "datetime", "real": "monetary value", "Group": "explanation"}, inplace=True)
-    all_anomalies['monetary value'] = all_anomalies['monetary value'].apply(lambda x: f"{x:.2f}")
-    all_anomalies = all_anomalies.fillna('').astype(str)
+    if 'all_anomalies' not in st.session_state:
+        with st.spinner('Aplicando modelo de série temporal...'):
+            # Load the file into a DataFrame
+            if uploaded_file.name.endswith('.csv'):
+                df = pd.read_csv(uploaded_file, quotechar='"', encoding='utf-8')
+            elif uploaded_file.name.endswith('.xlsx'):
+                df = pd.read_excel(uploaded_file)
+
+            # Data preprocessing for Prophet
+            new_df = df.iloc[2:, 9:-1].fillna(0)
+            new_df.columns = df.iloc[1, 9:-1]
+            new_df.columns = new_df.columns.str.replace(r" \(\d+\)", "", regex=True)
+
+            month_dict = {
+                'Jan': '01', 'Fev': '02', 'Mar': '03', 'Abr': '04',
+                'Mai': '05', 'Jun': '06', 'Jul': '07', 'Ago': '08',
+                'Set': '09', 'Out': '10', 'Nov': '11', 'Dez': '12'
+            }
+
+            def convert_column_name(column_name):
+                if column_name == 'Rótulos de Linha':
+                    return column_name
+                parts = column_name.split('/')
+                month = parts[0].strip()
+                year = parts[1].strip()
+                year = ''.join(filter(str.isdigit, year))
+                month_number = month_dict.get(month, '00')
+                return f"{month_number}/{year}"
+
+            new_df.columns = [convert_column_name(col) for col in new_df.columns]
+            new_df.columns = pd.to_datetime(new_df.columns, errors='coerce')
+            new_df.rename(columns={new_df.columns[0]: 'Rotulo'}, inplace=True)
+            df_clean = new_df.copy()
+
+            # Create an empty DataFrame to store all anomalies
+            all_anomalies = pd.DataFrame()
+
+            # Process each row in the DataFrame
+            for index, row in df_clean.iterrows():
+                data = pd.DataFrame({
+                    'ds': [col for col in df_clean.columns if isinstance(col, pd.Timestamp)],
+                    'y': row[[isinstance(col, pd.Timestamp) for col in df_clean.columns]].values
+                })
+
+                data = data[data['y'] > 0].reset_index(drop=True)
+                if data.empty or len(data) < 2:
+                    print(f"Skipping group {row['Rotulo']} because there are less than 2 non-zero observations.")
+                    continue
+
+                try:
+                    model = Prophet(interval_width=0.95)
+                    model.fit(data)
+                except ValueError as e:
+                    print(f"Skipping group {row['Rotulo']} due to error: {e}")
+                    continue
+
+                future = model.make_future_dataframe(periods=12, freq='M')
+                forecast = model.predict(future)
+
+                num_real = len(data)
+                num_forecast = len(forecast)
+                real_values = list(data['y']) + [None] * (num_forecast - num_real)
+                forecast['real'] = real_values
+                anomalies = forecast[(forecast['real'] < forecast['yhat_lower']) | (forecast['real'] > forecast['yhat_upper'])]
+
+                anomalies['Group'] = row['Rotulo']
+                all_anomalies = pd.concat([all_anomalies, anomalies[['ds', 'real', 'Group']]], ignore_index=True)
+
+            # Store the result in session state
+            all_anomalies.rename(columns={"ds": "datetime", "real": "monetary value", "Group": "group"}, inplace=True)
+            all_anomalies['monetary value'] = all_anomalies['monetary value'].apply(lambda x: f"{x:.2f}")
+            all_anomalies = all_anomalies.fillna('').astype(str)
+            st.session_state['all_anomalies'] = all_anomalies
 
     # Load translation models
     pt_en_translator = T5ForConditionalGeneration.from_pretrained("unicamp-dl/translation-pt-en-t5")
@@ -113,8 +116,7 @@ if uploaded_file:
         return response_pt
 
     # Streamlit interface
-
-    st.dataframe(all_anomalies.head())
+    st.dataframe(st.session_state['all_anomalies'].head())
 
     # Chat history
     if 'history' not in st.session_state:
@@ -126,7 +128,7 @@ if uploaded_file:
         st.session_state['history'].append(('👤', user_question))
         st.markdown(f"**👤 {user_question}**")
         
-        bot_response = response(user_question, all_anomalies)
+        bot_response = response(user_question, st.session_state['all_anomalies'])
         
         st.session_state['history'].append(('🤖', bot_response))
         st.markdown(f"<div style='text-align: right'>**🤖 {bot_response}**</div>", unsafe_allow_html=True)
@@ -140,4 +142,4 @@ if uploaded_file:
         elif sender == '🤖':
             st.markdown(f"<div style='text-align: right'>**🤖 {message}**</div>", unsafe_allow_html=True)
 else:
-    st.warning("Please upload a CSV or XLSX file to start.")
+    st.warning("Por favor, carregue um arquivo CSV ou XLSX para começar.")