add avg perg and vix em

app.py

@@ -126,7 +126,7 @@ with st.form("choose_model"):
                 operator = '<='
                 score = red_proba
                 # How many with this score?
-                cond = (res1['Predicted'] <= red_proba)
+                cond = (res1['Predicted'] <= seq_proba[0])
                 num_obs = len(res1.loc[cond])
                 # How often green?
                 historical_proba = 1 - res1.loc[cond, 'True'].mean()
@@ -152,8 +152,13 @@ with st.form("choose_model"):
 
             int_labels = ['(-∞, .20]', '(.20, .40]', '(.40, .60]', '(.60, .80]', '(.80, ∞]']
             # df_probas = res1.groupby(pd.qcut(res1['Predicted'],5)).agg({'True':[np.mean,len,np.sum]})
-            df_probas = res1.groupby(pd.cut(res1['Predicted'], bins = [-np.inf, 0.2, 0.4, 0.6, 0.8, np.inf], labels = int_labels)).agg({'True':[np.mean,len,np.sum]})
-            df_probas.columns = ['PctGreen','NumObs','NumGreen']
+
+            data['ClosePct'] = (data['Close'] / data['PrevClose']) - 1
+            data['ClosePct'] = data['ClosePct'].shift(-1)
+            res1 = res1.merge(data['ClosePct'], left_index=True,right_index=True)
+            df_probas = res1.groupby(pd.cut(res1['Predicted'], bins = [-np.inf, 0.2, 0.4, 0.6, 0.8, np.inf], labels = int_labels)).agg({'True':[np.mean,len,np.sum],'ClosePct':[np.mean]})
+            df_probas.columns = ['PctGreen','NumObs','NumGreen','AvgPerf']
+            df_probas['AvgPerf'] = df_probas['AvgPerf'].apply(lambda x: f'{x:.2%}')
 
             roc_auc_score_all = roc_auc_score(res1['True'].astype(int), res1['Predicted'].values)
             precision_score_all = precision_score(res1['True'].astype(int), res1['Predicted'] > 0.5)
@@ -225,12 +230,59 @@ with st.form("choose_model"):
             
             check = data.tail(1)
 
+            data['VIX_EM'] = data['Close'] * (data['Close_VIX']/100) * (np.sqrt( 1 ) / np.sqrt(252))
+            data['VIX_EM_High'] = data['Close'] + data['VIX_EM']
+            data['VIX_EM_Low'] = data['Close'] - data['VIX_EM']
+
+            data['VIX_EM_125'] = data['VIX_EM'] * 1.25
+            data['VIX_EM_125_High'] = data['Close'] + data['VIX_EM_125']
+            data['VIX_EM_125_Low'] = data['Close'] - data['VIX_EM_125']
+
+            data['VIX_EM_15'] = data['VIX_EM'] * 1.5
+            data['VIX_EM_15_High'] = data['Close'] + data['VIX_EM_15']
+            data['VIX_EM_15_Low'] = data['Close'] - data['VIX_EM_15']
+
+            data['VIX_EM'] = data['VIX_EM'].shift(1)
+            data['VIX_EM_High'] = data['VIX_EM_High'].shift(1)
+            data['VIX_EM_Low'] = data['VIX_EM_Low'].shift(1)
+
+            data['VIX_EM_15'] = data['VIX_EM_15'].shift(1)
+            data['VIX_EM_15_High'] = data['VIX_EM_15_High'].shift(1)
+            data['VIX_EM_15_Low'] = data['VIX_EM_15_Low'].shift(1)
+
+            data['VIX_EM_125'] = data['VIX_EM_125'].shift(1)
+            data['VIX_EM_125_High'] = data['VIX_EM_125_High'].shift(1)
+            data['VIX_EM_125_Low'] = data['VIX_EM_125_Low'].shift(1)
+
+            df_em = pd.DataFrame(columns=['EM','Low','High','WithinRange','Tested'])
+            df_em.loc['EM 1X'] = [
+                data['VIX_EM'].iloc[-1].round(2),
+                data['VIX_EM_Low'].iloc[-1].round(2), 
+                data['VIX_EM_High'].iloc[-1].round(2), 
+                f"{len(data.query('Close <= VIX_EM_High & Close >= VIX_EM_Low')) / len(data):.1%}",
+                f"{len(data.query('High > VIX_EM_High | Low < VIX_EM_Low')) / len(data):.1%}"
+                ]
+            df_em.loc['EM 1.25X'] = [
+                data['VIX_EM_125'].iloc[-1].round(2),
+                data['VIX_EM_125_Low'].iloc[-1].round(2), 
+                data['VIX_EM_125_High'].iloc[-1].round(2), 
+                f"{len(data.query('Close <= VIX_EM_125_High & Close >= VIX_EM_125_Low')) / len(data):.1%}",
+                f"{len(data.query('High > VIX_EM_125_High | Low < VIX_EM_125_Low')) / len(data):.1%}"
+                ]
+            df_em.loc[f"EM 1.5X"] = [
+                data['VIX_EM_15'].iloc[-1].round(2),
+                data['VIX_EM_15_Low'].iloc[-1].round(2), 
+                data['VIX_EM_15_High'].iloc[-1].round(2), 
+                f"{len(data.query('Close <= VIX_EM_15_High & Close >= VIX_EM_15_Low')) / len(data):.1%}",
+                f"{len(data.query('High > VIX_EM_15_High | Low < VIX_EM_15_Low')) / len(data):.1%}"
+                ]
+            
             with tab1:
-                st.subheader(f'Pred for {curr_date} as of 7AM PST')
+                st.subheader(f'Pred for {curr_date} as of 6:30AM PST')
                 st.write(results)
                 st.write(df_probas)
-                st.text('For checking only 👇🏽')
-                st.write(check)
+                st.text('VIX EM')
+                st.write(df_em)
             with tab2:
                 st.subheader('Latest Data for Pred')
                 st.write(new_pred)
@@ -352,7 +404,7 @@ with st.form("choose_model"):
                 operator = '<='
                 score = red_proba
                 # How many with this score?
-                cond = (res1['Predicted'] <= red_proba)
+                cond = (res1['Predicted'] <= seq_proba[0])
                 num_obs = len(res1.loc[cond])
                 # How often green?
                 historical_proba = 1 - res1.loc[cond, 'True'].mean()
@@ -378,9 +430,14 @@ with st.form("choose_model"):
 
             int_labels = ['(-∞, .20]', '(.20, .40]', '(.40, .60]', '(.60, .80]', '(.80, ∞]']
             # df_probas = res1.groupby(pd.qcut(res1['Predicted'],5)).agg({'True':[np.mean,len,np.sum]})
-            df_probas = res1.groupby(pd.cut(res1['Predicted'], bins = [-np.inf, 0.2, 0.4, 0.6, 0.8, np.inf], labels = int_labels)).agg({'True':[np.mean,len,np.sum]})
-            df_probas.columns = ['PctGreen','NumObs','NumGreen']
-
+            
+            data['ClosePct'] = (data['Close'] / data['PrevClose']) - 1
+            data['ClosePct'] = data['ClosePct'].shift(-1)
+            res1 = res1.merge(data['ClosePct'], left_index=True,right_index=True)
+            df_probas = res1.groupby(pd.cut(res1['Predicted'], bins = [-np.inf, 0.2, 0.4, 0.6, 0.8, np.inf], labels = int_labels)).agg({'True':[np.mean,len,np.sum],'ClosePct':[np.mean]})
+            df_probas.columns = ['PctGreen','NumObs','NumGreen','AvgPerf']
+            df_probas['AvgPerf'] = df_probas['AvgPerf'].apply(lambda x: f'{x:.2%}')
+            
             roc_auc_score_all = roc_auc_score(res1['True'].astype(int), res1['Predicted'].values)
             precision_score_all = precision_score(res1['True'].astype(int), res1['Predicted'] > 0.5)
             recall_score_all = recall_score(res1['True'].astype(int), res1['Predicted'] > 0.5)
@@ -451,12 +508,59 @@ with st.form("choose_model"):
 
             check = data.tail(1)
 
+            data['VIX_EM'] = data['Close'] * (data['Close_VIX']/100) * (np.sqrt( 1 ) / np.sqrt(252))
+            data['VIX_EM_High'] = data['Close'] + data['VIX_EM']
+            data['VIX_EM_Low'] = data['Close'] - data['VIX_EM']
+
+            data['VIX_EM_125'] = data['VIX_EM'] * 1.25
+            data['VIX_EM_125_High'] = data['Close'] + data['VIX_EM_125']
+            data['VIX_EM_125_Low'] = data['Close'] - data['VIX_EM_125']
+
+            data['VIX_EM_15'] = data['VIX_EM'] * 1.5
+            data['VIX_EM_15_High'] = data['Close'] + data['VIX_EM_15']
+            data['VIX_EM_15_Low'] = data['Close'] - data['VIX_EM_15']
+
+            data['VIX_EM'] = data['VIX_EM'].shift(1)
+            data['VIX_EM_High'] = data['VIX_EM_High'].shift(1)
+            data['VIX_EM_Low'] = data['VIX_EM_Low'].shift(1)
+
+            data['VIX_EM_15'] = data['VIX_EM_15'].shift(1)
+            data['VIX_EM_15_High'] = data['VIX_EM_15_High'].shift(1)
+            data['VIX_EM_15_Low'] = data['VIX_EM_15_Low'].shift(1)
+
+            data['VIX_EM_125'] = data['VIX_EM_125'].shift(1)
+            data['VIX_EM_125_High'] = data['VIX_EM_125_High'].shift(1)
+            data['VIX_EM_125_Low'] = data['VIX_EM_125_Low'].shift(1)
+
+            df_em = pd.DataFrame(columns=['EM','Low','High','WithinRange','Tested'])
+            df_em.loc['EM 1X'] = [
+                data['VIX_EM'].iloc[-1].round(2),
+                data['VIX_EM_Low'].iloc[-1].round(2), 
+                data['VIX_EM_High'].iloc[-1].round(2), 
+                f"{len(data.query('Close <= VIX_EM_High & Close >= VIX_EM_Low')) / len(data):.1%}",
+                f"{len(data.query('High > VIX_EM_High | Low < VIX_EM_Low')) / len(data):.1%}"
+                ]
+            df_em.loc['EM 1.25X'] = [
+                data['VIX_EM_125'].iloc[-1].round(2),
+                data['VIX_EM_125_Low'].iloc[-1].round(2), 
+                data['VIX_EM_125_High'].iloc[-1].round(2), 
+                f"{len(data.query('Close <= VIX_EM_125_High & Close >= VIX_EM_125_Low')) / len(data):.1%}",
+                f"{len(data.query('High > VIX_EM_125_High | Low < VIX_EM_125_Low')) / len(data):.1%}"
+                ]
+            df_em.loc[f"EM 1.5X"] = [
+                data['VIX_EM_15'].iloc[-1].round(2),
+                data['VIX_EM_15_Low'].iloc[-1].round(2), 
+                data['VIX_EM_15_High'].iloc[-1].round(2), 
+                f"{len(data.query('Close <= VIX_EM_15_High & Close >= VIX_EM_15_Low')) / len(data):.1%}",
+                f"{len(data.query('High > VIX_EM_15_High | Low < VIX_EM_15_Low')) / len(data):.1%}"
+                ]
+            
             with tab1:
                 st.subheader(f'Pred for {curr_date} as of 7AM PST')
                 st.write(results)
                 st.write(df_probas)
-                st.text('For checking only 👇🏽')
-                st.write(check)
+                st.text('VIX EM')
+                st.write(df_em)
             with tab2:
                 st.subheader('Latest Data for Pred')
                 st.write(new_pred)
@@ -578,7 +682,7 @@ with st.form("choose_model"):
                 operator = '<='
                 score = red_proba
                 # How many with this score?
-                cond = (res1['Predicted'] <= red_proba)
+                cond = (res1['Predicted'] <= seq_proba[0])
                 num_obs = len(res1.loc[cond])
                 # How often green?
                 historical_proba = 1 - res1.loc[cond, 'True'].mean()
@@ -603,8 +707,13 @@ with st.form("choose_model"):
             # st.subheader('New Prediction')
             int_labels = ['(-∞, .20]', '(.20, .40]', '(.40, .60]', '(.60, .80]', '(.80, ∞]']
             # df_probas = res1.groupby(pd.qcut(res1['Predicted'],5)).agg({'True':[np.mean,len,np.sum]})
-            df_probas = res1.groupby(pd.cut(res1['Predicted'], bins = [-np.inf, 0.2, 0.4, 0.6, 0.8, np.inf], labels = int_labels)).agg({'True':[np.mean,len,np.sum]})
-            df_probas.columns = ['PctGreen','NumObs','NumGreen']
+            
+            data['ClosePct'] = (data['Close'] / data['PrevClose']) - 1
+            data['ClosePct'] = data['ClosePct'].shift(-1)
+            res1 = res1.merge(data['ClosePct'], left_index=True,right_index=True)
+            df_probas = res1.groupby(pd.cut(res1['Predicted'], bins = [-np.inf, 0.2, 0.4, 0.6, 0.8, np.inf], labels = int_labels)).agg({'True':[np.mean,len,np.sum],'ClosePct':[np.mean]})
+            df_probas.columns = ['PctGreen','NumObs','NumGreen','AvgPerf']
+            df_probas['AvgPerf'] = df_probas['AvgPerf'].apply(lambda x: f'{x:.2%}')
 
             roc_auc_score_all = roc_auc_score(res1['True'].astype(int), res1['Predicted'].values)
             precision_score_all = precision_score(res1['True'].astype(int), res1['Predicted'] > 0.5)
@@ -676,12 +785,59 @@ with st.form("choose_model"):
             
             check = data.tail(1)
 
+            data['VIX_EM'] = data['Close'] * (data['Close_VIX']/100) * (np.sqrt( 1 ) / np.sqrt(252))
+            data['VIX_EM_High'] = data['Close'] + data['VIX_EM']
+            data['VIX_EM_Low'] = data['Close'] - data['VIX_EM']
+
+            data['VIX_EM_125'] = data['VIX_EM'] * 1.25
+            data['VIX_EM_125_High'] = data['Close'] + data['VIX_EM_125']
+            data['VIX_EM_125_Low'] = data['Close'] - data['VIX_EM_125']
+
+            data['VIX_EM_15'] = data['VIX_EM'] * 1.5
+            data['VIX_EM_15_High'] = data['Close'] + data['VIX_EM_15']
+            data['VIX_EM_15_Low'] = data['Close'] - data['VIX_EM_15']
+
+            data['VIX_EM'] = data['VIX_EM'].shift(1)
+            data['VIX_EM_High'] = data['VIX_EM_High'].shift(1)
+            data['VIX_EM_Low'] = data['VIX_EM_Low'].shift(1)
+
+            data['VIX_EM_15'] = data['VIX_EM_15'].shift(1)
+            data['VIX_EM_15_High'] = data['VIX_EM_15_High'].shift(1)
+            data['VIX_EM_15_Low'] = data['VIX_EM_15_Low'].shift(1)
+
+            data['VIX_EM_125'] = data['VIX_EM_125'].shift(1)
+            data['VIX_EM_125_High'] = data['VIX_EM_125_High'].shift(1)
+            data['VIX_EM_125_Low'] = data['VIX_EM_125_Low'].shift(1)
+
+            df_em = pd.DataFrame(columns=['EM','Low','High','WithinRange','Tested'])
+            df_em.loc['EM 1X'] = [
+                data['VIX_EM'].iloc[-1].round(2),
+                data['VIX_EM_Low'].iloc[-1].round(2), 
+                data['VIX_EM_High'].iloc[-1].round(2), 
+                f"{len(data.query('Close <= VIX_EM_High & Close >= VIX_EM_Low')) / len(data):.1%}",
+                f"{len(data.query('High > VIX_EM_High | Low < VIX_EM_Low')) / len(data):.1%}"
+                ]
+            df_em.loc['EM 1.25X'] = [
+                data['VIX_EM_125'].iloc[-1].round(2),
+                data['VIX_EM_125_Low'].iloc[-1].round(2), 
+                data['VIX_EM_125_High'].iloc[-1].round(2), 
+                f"{len(data.query('Close <= VIX_EM_125_High & Close >= VIX_EM_125_Low')) / len(data):.1%}",
+                f"{len(data.query('High > VIX_EM_125_High | Low < VIX_EM_125_Low')) / len(data):.1%}"
+                ]
+            df_em.loc[f"EM 1.5X"] = [
+                data['VIX_EM_15'].iloc[-1].round(2),
+                data['VIX_EM_15_Low'].iloc[-1].round(2), 
+                data['VIX_EM_15_High'].iloc[-1].round(2), 
+                f"{len(data.query('Close <= VIX_EM_15_High & Close >= VIX_EM_15_Low')) / len(data):.1%}",
+                f"{len(data.query('High > VIX_EM_15_High | Low < VIX_EM_15_Low')) / len(data):.1%}"
+                ]
+            
             with tab1:
                 st.subheader(f'Pred for {curr_date} as of 7:30AM PST')
                 st.write(results)
                 st.write(df_probas)
-                st.text('For checking only 👇🏽')
-                st.write(check)
+                st.text('VIX EM')
+                st.write(df_em)
             with tab2:
                 st.subheader('Latest Data for Pred')
                 st.write(new_pred)
@@ -696,7 +852,7 @@ with st.form("choose_model"):
                 #     label="Download Historical Performance",
                 #     data=csv,
                 fname='performance_for_60m_model.csv'
-                # )
+                # )                
 
         elif option == '🕰 90 Mins':
         # run60 = st.button('🏃🏽‍♂️ Run')
@@ -803,7 +959,7 @@ with st.form("choose_model"):
                 operator = '<='
                 score = red_proba
                 # How many with this score?
-                cond = (res1['Predicted'] <= red_proba)
+                cond = (res1['Predicted'] <= seq_proba[0])
                 num_obs = len(res1.loc[cond])
                 # How often green?
                 historical_proba = 1 - res1.loc[cond, 'True'].mean()
@@ -828,8 +984,13 @@ with st.form("choose_model"):
             # st.subheader('New Prediction')
             int_labels = ['(-∞, .20]', '(.20, .40]', '(.40, .60]', '(.60, .80]', '(.80, ∞]']
             # df_probas = res1.groupby(pd.qcut(res1['Predicted'],5)).agg({'True':[np.mean,len,np.sum]})
-            df_probas = res1.groupby(pd.cut(res1['Predicted'], bins = [-np.inf, 0.2, 0.4, 0.6, 0.8, np.inf], labels = int_labels)).agg({'True':[np.mean,len,np.sum]})
-            df_probas.columns = ['PctGreen','NumObs','NumGreen']
+            
+            data['ClosePct'] = (data['Close'] / data['PrevClose']) - 1
+            data['ClosePct'] = data['ClosePct'].shift(-1)
+            res1 = res1.merge(data['ClosePct'], left_index=True,right_index=True)
+            df_probas = res1.groupby(pd.cut(res1['Predicted'], bins = [-np.inf, 0.2, 0.4, 0.6, 0.8, np.inf], labels = int_labels)).agg({'True':[np.mean,len,np.sum],'ClosePct':[np.mean]})
+            df_probas.columns = ['PctGreen','NumObs','NumGreen','AvgPerf']
+            df_probas['AvgPerf'] = df_probas['AvgPerf'].apply(lambda x: f'{x:.2%}')
 
             roc_auc_score_all = roc_auc_score(res1['True'].astype(int), res1['Predicted'].values)
             precision_score_all = precision_score(res1['True'].astype(int), res1['Predicted'] > 0.5)
@@ -901,12 +1062,59 @@ with st.form("choose_model"):
             
             check = data.tail(1)
 
+            data['VIX_EM'] = data['Close'] * (data['Close_VIX']/100) * (np.sqrt( 1 ) / np.sqrt(252))
+            data['VIX_EM_High'] = data['Close'] + data['VIX_EM']
+            data['VIX_EM_Low'] = data['Close'] - data['VIX_EM']
+
+            data['VIX_EM_125'] = data['VIX_EM'] * 1.25
+            data['VIX_EM_125_High'] = data['Close'] + data['VIX_EM_125']
+            data['VIX_EM_125_Low'] = data['Close'] - data['VIX_EM_125']
+
+            data['VIX_EM_15'] = data['VIX_EM'] * 1.5
+            data['VIX_EM_15_High'] = data['Close'] + data['VIX_EM_15']
+            data['VIX_EM_15_Low'] = data['Close'] - data['VIX_EM_15']
+
+            data['VIX_EM'] = data['VIX_EM'].shift(1)
+            data['VIX_EM_High'] = data['VIX_EM_High'].shift(1)
+            data['VIX_EM_Low'] = data['VIX_EM_Low'].shift(1)
+
+            data['VIX_EM_15'] = data['VIX_EM_15'].shift(1)
+            data['VIX_EM_15_High'] = data['VIX_EM_15_High'].shift(1)
+            data['VIX_EM_15_Low'] = data['VIX_EM_15_Low'].shift(1)
+
+            data['VIX_EM_125'] = data['VIX_EM_125'].shift(1)
+            data['VIX_EM_125_High'] = data['VIX_EM_125_High'].shift(1)
+            data['VIX_EM_125_Low'] = data['VIX_EM_125_Low'].shift(1)
+
+            df_em = pd.DataFrame(columns=['EM','Low','High','WithinRange','Tested'])
+            df_em.loc['EM 1X'] = [
+                data['VIX_EM'].iloc[-1].round(2),
+                data['VIX_EM_Low'].iloc[-1].round(2), 
+                data['VIX_EM_High'].iloc[-1].round(2), 
+                f"{len(data.query('Close <= VIX_EM_High & Close >= VIX_EM_Low')) / len(data):.1%}",
+                f"{len(data.query('High > VIX_EM_High | Low < VIX_EM_Low')) / len(data):.1%}"
+                ]
+            df_em.loc['EM 1.25X'] = [
+                data['VIX_EM_125'].iloc[-1].round(2),
+                data['VIX_EM_125_Low'].iloc[-1].round(2), 
+                data['VIX_EM_125_High'].iloc[-1].round(2), 
+                f"{len(data.query('Close <= VIX_EM_125_High & Close >= VIX_EM_125_Low')) / len(data):.1%}",
+                f"{len(data.query('High > VIX_EM_125_High | Low < VIX_EM_125_Low')) / len(data):.1%}"
+                ]
+            df_em.loc[f"EM 1.5X"] = [
+                data['VIX_EM_15'].iloc[-1].round(2),
+                data['VIX_EM_15_Low'].iloc[-1].round(2), 
+                data['VIX_EM_15_High'].iloc[-1].round(2), 
+                f"{len(data.query('Close <= VIX_EM_15_High & Close >= VIX_EM_15_Low')) / len(data):.1%}",
+                f"{len(data.query('High > VIX_EM_15_High | Low < VIX_EM_15_Low')) / len(data):.1%}"
+                ]
+            
             with tab1:
                 st.subheader(f'Pred for {curr_date} as of 8AM PST')
                 st.write(results)
                 st.write(df_probas)
-                st.text('For checking only 👇🏽')
-                st.write(check)
+                st.text('VIX EM')
+                st.write(df_em)
             with tab2:
                 st.subheader('Latest Data for Pred')
                 st.write(new_pred)
@@ -921,7 +1129,7 @@ with st.form("choose_model"):
                 #     label="Download Historical Performance",
                 #     data=csv,
                 fname='performance_for_90m_model.csv'
-                # )
+                # )                
 
 if submitted:
     st.download_button(

model_1h.py

@@ -236,7 +236,7 @@ def get_data():
     last_date = last_date + datetime.timedelta(days=1)
     # Get incremental data
     spx1 = yf.Ticker('^GSPC')
-    yfp = spx1.history(start=last_date, interval='60m')
+    yfp = spx1.history(start=last_date, interval='30m')
     # Concat current and incremental
     df_30m = pd.concat([fr, yfp])
     # Get the first 30 minute bar

model_90m.py

@@ -236,7 +236,7 @@ def get_data():
     last_date = last_date + datetime.timedelta(days=1)
     # Get incremental data
     spx1 = yf.Ticker('^GSPC')
-    yfp = spx1.history(start=last_date, interval='90m')
+    yfp = spx1.history(start=last_date, interval='30m')
     # Concat current and incremental
     df_30m = pd.concat([fr, yfp])
     # Get the first 30 minute bar