Update app.py

app.py

@@ -15,13 +15,13 @@ 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: 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: green; margin-right: 0px;'></div>
+        <div style='width: 20px; height: 4px; background-color: red; margin-right: 0px;'></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>
+        <span style='font-size: 40px; 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'>
+        <span style='font-size: 24px; font-weight: normal; color: #333; font-family: "Kanit", sans-serif'>
         Meta Prophet + Microsoft TAPEX</span>
     </div>
 </div>
@@ -65,8 +65,39 @@ def load_data(uploaded_file):
     return df
 
 def preprocess_data(df):
-    # Implementar as etapas de pré-processamento aqui
-    return df
+    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):
+        # Check if the column name is 'Rótulos de Linha'
+        if column_name == 'Rótulos de Linha':
+            return column_name
+    
+        # Otherwise, proceed to convert
+        parts = column_name.split('/')
+        month = parts[0].strip()
+        year = parts[1].strip()
+    
+        # Clean year in case there are extra characters
+        year = ''.join(filter(str.isdigit, year))
+    
+        # Get month number from the dictionary
+        month_number = month_dict.get(month, '00')  # Default '00' if month is not found
+    
+        # Return formatted date string
+        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):
     if df_clean.empty:
@@ -77,8 +108,41 @@ def apply_prophet(df_clean):
     all_anomalies = pd.DataFrame()
     # Processar cada linha no DataFrame
     for index, row in df_clean.iterrows():
-        # Implementar o processamento com o modelo Prophet aqui
-        pass  # Substituir pass pelo seu código real
+        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
+        })
+    
+        # Remove lines where 'y' is zero until the first non-zero value
+        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 to create and train the model
+        try:
+            model = Prophet(interval_width=0.95)  # Confidence interval
+            model.fit(data)
+        except ValueError as e:
+            print(f"Skipping group {row['Rotulo']} due to error: {e}")
+            continue
+    
+        # Make future predictions
+        future = model.make_future_dataframe(periods=12, freq='M')
+        forecast = model.predict(future)
+    
+        # Identify points outside the confidence interval
+        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'])]
+    
+        # Add group label to the anomalies
+        anomalies['group'] = row['Rotulo']
+    
+        # Append anomalies to the all_anomalies DataFrame
+        all_anomalies = pd.concat([all_anomalies, anomalies[['ds', 'real', 'group']]], ignore_index=True)
 
     # Renomear colunas e aplicar filtros
     return all_anomalies