Update app.py

app.py

@@ -8,10 +8,11 @@ import japanize_matplotlib
 import matplotlib.dates as mdates
 from dateutil.relativedelta import relativedelta
 import datetime
+import datarobot as dr
 from function import get_fish_qty, get_estat, dr_prediction_deployment, prediction_func, train_modeling
 
 import yaml
-with open('config/config.yaml') as file:
+with open('config.yaml') as file:
     config = yaml.safe_load(file.read())
     
 def retrain():
@@ -34,48 +35,119 @@ def get_prediction_result(retrain = False):
                   how='left')
     df.loc[df['forecast_point'].isnull(), 'forecast_point'] = df['target_date'].apply(lambda x:x-relativedelta(months=1))
     df = df.loc[~((df['target_date']<(today+relativedelta(months=1)))&(df['電気代'].isnull()))]
-    return df[['forecast_point', 'target_date', '電気代']]
+    df = df.rename(columns={'電気代':'電気代_予測'})
+    return df[['forecast_point', 'target_date', '電気代_予測']]
 
 def plot_prediction_result():
     update = gr.LinePlot.update(
         value=get_prediction_result(),
         x="target_date",
-        y="電気代",
+        y="電気代_予測",
         title="昨日までの魚の卸売り量から予測された、来月の2人世帯の平均電気料金の推移",
         width=500,
-        height=400,
+        height=300,
     )
     return update
-# def plot_prediction_result():
-#     df = get_prediction_result()
+    
+def get_train_newest_target_period():
+    df = pd.read_csv('data/train.csv')
+    train_max_yearmonth = pd.to_datetime(str(df['年月'].max()), format='%Y%m').strftime('%Y年%m月')
+    return train_max_yearmonth
+    
+def get_newest_target_period():
+    df = get_estat.get_household_survey()
+    expence_df = pd.DataFrame({'年月':df['時間軸（月次）'].unique()})
+    cate='3.1 電気代'
+    temp_df = df.loc[df['品目分類（2020年改定）'] == cate]
+    unit = temp_df['unit'].unique()[0]
+    temp_df = temp_df.rename(columns={'value':f'{cate}_({unit})'})
+    expence_df = pd.merge(expence_df,
+                          temp_df[['時間軸（月次）', f'{cate}_({unit})']].rename(columns={'時間軸（月次）':'年月'}),
+                          on='年月',
+                          how='left')
+    expence_df = expence_df.rename(columns={'3.1 電気代_(円)':'電気代'})
+    expence_df['年月'] = pd.to_datetime(expence_df['年月'], format='%Y年%m月').astype(str).apply(lambda x:''.join(x.split('-'))[:6]).astype(int)
+    target_max_yearmonth = pd.to_datetime(str(expence_df['年月'].max()), format='%Y%m').strftime('%Y年%m月')
+    
+    return target_max_yearmonth
 
-#     fig, ax1 = plt.subplots(1, 1, figsize=(30, 10))
-#     fig.autofmt_xdate()
-#     ax1.xaxis.set_major_formatter(mdates.DateFormatter("%Y/%m/%d"))
-#     ax1.xaxis.set_major_locator(mdates.DayLocator(interval=1))
-#     plt.rcParams["font.size"] = 14
-#     ax1.grid(True)
-#     ax1.set_xlim(df['target_date'].min(), df['target_date'].max())
-#     ax1.set_xlabel('target_date')
-#     ax1.set_ylabel('電気代（円）')
-#     ax1.plot(df['target_date'], df['電気代'])
-#     ax1.legend(loc="upper left", bbox_to_anchor=(1.0, 1.0))
+def get_model_infomation():
+    token = 'NjQwMDVmNGI0ZDQzZDFhYzI2YThmZDJiOnVZejljTXFNTXNoUnlKMStoUFhXSFdYMEZRck9lY3dobnEvRFZ1aVBHbVE9'
+    ### デモ環境これっぽい
+    endpoint = 'https://app.datarobot.com/api/v2' 
+    dr.Client(
+                        endpoint=endpoint,
+                        token=token
+                    )
+    model_info = pd.read_csv('data/model_management.csv').iloc[-1, :]
+    model = dr.Model.get(project = dr.Project.get(model_info['model_url'].split('/')[4]), model_id = model_info['model_url'].split('/')[-1])
     
-    return fig
+    feature_impact = pd.DataFrame(model.get_or_request_feature_impact())
+    feature_impact = feature_impact.sort_values('impactNormalized', ascending=False).reset_index(drop=True)
+    feature_impact = feature_impact.iloc[:20, :]
+    
+    return model_info, feature_impact
 
 
 with gr.Blocks() as electoric_ploting:
-    gr.Markdown("# 📈 Real-Time Line Plot")
+    gr.Markdown(
+                            """
+                            # その日の魚の卸売り量から、来月の家計データ月別支出の電気代を予測するAI
+                            使用データ  
+                             * 東京卸売市場日報
+                             * 家計調査の月別支出
+                             * 原油価格データ
+                             * 燃料調達価格データ  
+                            why  
+                            電気代のtrendは原油価格などが大きく影響するが、細かい変化は気候に影響し、気候はある程度海水温に関連性があると考えられる。
+                            また、魚の卸売量は水揚げ量に関係し、水揚げ量は海水温に関係するという考えからモデルを作成。
+                             """
+                        )
     with gr.Row():
         with gr.Column():
             plot = gr.LinePlot(show_label=False)
 #             plot = gr.Plot(label="昨日までの魚の卸売り量から予測された、来月の2人世帯の平均電気料金の推移")
+        with gr.Column():
+            df = get_prediction_result()
+            gr.Textbox(df['電気代_予測'].max(),
+                            label='現在までの予測値の最大値')
+            gr.Textbox(df['電気代_予測'].min(),
+                            label='現在までの予測値の最小値')
+            gr.Textbox(df['電気代_予測'].mean(),
+                            label='現在までの予測値の平均値')
+            gr.Textbox(df['電気代_予測'].median(),
+                            label='現在までの予測値の中央値')
     with gr.Row():
         gr.DataFrame(get_prediction_result)
 
         with gr.Column():
+            
+            gr.Textbox(get_train_newest_target_period,
+                            label='現在の学習済みのターゲット値最新月')
+            gr.Textbox(get_newest_target_period,
+                            label='現在の取得可能ターゲット値最新月')
             btn= gr.Button(value="再学習")
             btn.click(retrain, inputs=None, outputs=None)
+            
+            with gr.Row():
+                model_info, feature_impact_df = get_model_infomation()
+                gr.Textbox(model_info['model_type'],
+                            label='現在のモデル')
+            with gr.Row():
+                for i in range(len(feature_impact_df)):
+                    feature_impact_df['featureName'][i] = str(i+1).zfill(2) + '_' + feature_impact_df['featureName'][i]
+                gr.BarPlot(value = feature_impact_df,
+                                title = '特徴量インパクト上位20',
+                                x = 'featureName',
+                                y = 'impactNormalized',
+                                tooltip=['impactNormalized'],
+                                x_title = '特徴量名',
+                                y_title = '特徴量インパクト_相対値',
+                                vertical=False,
+                                y_lim=[0, 1.2],
+                                width=400,
+                                height=300)
+                
         
 
     # demo.load(make_plot, inputs=[button], outputs=[plot])