Update app.py

app.py

@@ -68,20 +68,92 @@ def load_data(uploaded_file):
     return df
 
 def preprocess_data(df):
-    # Implementar as etapas de pré-processamento aqui
-    return 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
+
+def apply_prophet(df_clean):
+    # 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)
+
+    # 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
 
-def apply_prophet(df):
-    # Implementar o modelo Prophet aqui
-    return df
-    
 # Interface para carregar arquivo
 uploaded_file = st.file_uploader("Carregue um arquivo CSV ou XLSX", type=['csv', 'xlsx'])
-if uploaded_file and 'all_anomalies' not in st.session_state:
-    df = load_data(uploaded_file)
-    df = preprocess_data(df)
-    all_anomalies = apply_prophet(df)
-    st.session_state['all_anomalies'] = all_anomalies
+if uploaded_file:
+    if 'all_anomalies' not in st.session_state:
+        df = load_data(uploaded_file)
+        df = preprocess_data(df)
+        with st.spinner('Aplicando modelo de série temporal...'):
+            all_anomalies = apply_prophet(df)
+            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:", "")