Update app.py

app.py

@@ -3,11 +3,8 @@ import pandas as pd
 from transformers import BartForConditionalGeneration, TapexTokenizer, T5ForConditionalGeneration, T5Tokenizer
 from prophet import Prophet
 
-# Caminho para o arquivo CSS, ajuste conforme a estrutura do seu projeto
-css_file = "style.css"
-
 # Abrindo e lendo o arquivo CSS
-with open(css_file, "r") as css:
+with open("style.css", "r") as css:
     css_style = css.read()
 
 # Markdown combinado com a importação da fonte e o HTML
@@ -18,10 +15,10 @@ html_content = f"""
 </style>
 <div style='display: flex; flex-direction: column; align-items: flex-start;'>
     <div style='display: flex; align-items: center;'>
-        <div style='width: 20px; height: 40px; background-color: green; margin-right: 1px;'></div>
-        <div style='width: 20px; height: 40px; background-color: red; margin-right: 1px;'></div>
-        <div style='width: 20px; height: 40px; background-color: yellow; margin-right: 20px;'></div>
-        <span style='font-size: 50px; font-weight: normal; font-family: "Kanit", sans-serif;'>NOSTRADAMUS</span>
+        <div style='width: 20px; height: 4px; background-color: green; margin-right: 1px;'></div>
+        <div style='width: 20px; height: 4px; background-color: red; margin-right: 1px;'></div>
+        <div style='width: 20px; height: 4px; background-color: yellow; margin-right: 20px;'></div>
+        <span style='font-size: 45px; font-weight: normal; font-family: "Kanit", sans-serif;'>NOSTRADAMUS</span>
     </div>
     <div style='text-align: left; width: 100%;'>
         <span style='font-size: 20px; font-weight: normal; color: #333; font-family: "Kanit", sans-serif'>
@@ -68,99 +65,45 @@ def load_data(uploaded_file):
     return df
 
 def preprocess_data(df):
-    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()
-    return df_clean
+    # Implementar as etapas de pré-processamento aqui
+    return df
 
 def apply_prophet(df_clean):
+    if df_clean.empty:
+        st.error("DataFrame está vazio após o pré-processamento.")
+        return pd.DataFrame()
+
     # Criar um DataFrame vazio para armazenar todas as anomalias
     all_anomalies = pd.DataFrame()
-
     # Processar cada linha no 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"Pulando grupo {row['Rotulo']} porque há menos de 2 observações não nulas.")
-            continue
-
-        try:
-            model = Prophet(interval_width=0.95)
-            model.fit(data)
-        except ValueError as e:
-            print(f"Pulando grupo {row['Rotulo']} devido a erro: {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)
+        # Implementar o processamento com o modelo Prophet aqui
+        pass  # Substituir pass pelo seu código real
 
     # Renomear colunas e aplicar filtros
-    all_anomalies.rename(columns={"ds": "datetime", "real": "monetary value", "Group": "group"}, inplace=True)
-    all_anomalies = all_anomalies[all_anomalies['monetary value'].astype(float) >= 10000000.00]
-    all_anomalies['monetary value'] = all_anomalies['monetary value'].apply(lambda x: f"{x:.2f}")
-    all_anomalies.sort_values(by=['monetary value'], ascending=False, inplace=True)
-    all_anomalies = all_anomalies.fillna('').astype(str)
-
     return all_anomalies
 
 # Interface para carregar arquivo
 uploaded_file = st.file_uploader("Carregue um arquivo CSV ou XLSX", type=['csv', 'xlsx'])
 if uploaded_file:
-    if 'all_anomalies' not in st.session_state:
-        df = load_data(uploaded_file)
-        df = preprocess_data(df)
+    df = load_data(uploaded_file)
+    df_clean = preprocess_data(df)
+    if df_clean.empty:
+        st.warning("Não há dados válidos para processar.")
+    else:
         with st.spinner('Aplicando modelo de série temporal...'):
-            all_anomalies = apply_prophet(df)
+            all_anomalies = apply_prophet(df_clean)
             st.session_state['all_anomalies'] = all_anomalies
-        st.session_state['all_anomalies'] = all_anomalies
 
 # Interface para perguntas do usuário
 user_question = st.text_input("Escreva sua questão aqui:", "")
 if user_question:
-    bot_response = response(user_question, st.session_state['all_anomalies'])
-    st.session_state['history'].append(('👤', user_question))
-    st.session_state['history'].append(('🤖', bot_response))
+    if 'all_anomalies' in st.session_state and not st.session_state['all_anomalies'].empty:
+        bot_response = response(user_question, st.session_state['all_anomalies'])
+        st.session_state['history'].append(('👤', user_question))
+        st.session_state['history'].append(('🤖', bot_response))
+    else:
+        st.warning("Ainda não há dados de anomalias para responder a pergunta.")
 
 # Mostrar histórico de conversa
 for sender, message in st.session_state['history']:
@@ -171,4 +114,4 @@ for sender, message in st.session_state['history']:
 
 # Botão para limpar histórico
 if st.button("Limpar histórico"):
-    st.session_state['history'] = []
+    st.session_state['history'] = []