tidied

src/scripts/climate_change/linear_model_historical_realtionship_reporting_precipitation.py

@@ -66,7 +66,7 @@ def create_binary_feature(threshold, weather_data_df, recent_months):
 above_below_average = create_binary_feature(
     grouped_data.groupby(['facility', 'month'])['weather_data'].transform('mean'), weather_data_historical, 0
 )
-above_below_X = create_binary_feature(800, weather_data_historical, 12)
+above_below_X = create_binary_feature(1000, weather_data_historical, 12)
 
 # Prepare additional facility info
 expanded_facility_info = pd.read_csv("/Users/rem76/Desktop/Climate_change_health/Data/expanded_facility_info_by_smaller_facility_lm.csv", index_col=0)
@@ -92,7 +92,7 @@ def repeat_info(info, num_facilities, year_range):
     year_flattened,
     month_flattened,
     above_below_average,
-    above_below_X,
+    #above_below_X,
     #facility_encoded,
     resid_encoded,
     zone_encoded,
@@ -103,9 +103,9 @@ def repeat_info(info, num_facilities, year_range):
 
 #scaler = StandardScaler() # as weather is at such different levels
 #X_scaled = scaler.fit_transform(X)
-results = build_model(X, y, scale_y=False, binomial=False, X_mask_mm = 0)
+results = build_model(X, y, scale_y=False, binomial=False, X_mask_mm = 800)
 print(results.summary())
 
-results = build_model(X, y, X_mask_mm = 0)
+results = build_model(X, y, X_mask_mm = 800)
 
 print(results.summary())

src/scripts/climate_change/reporting_and_weather_data_small_facilities.py

@@ -109,9 +109,6 @@
 monthly_reporting_by_facility = monthly_reporting_by_facility.loc[:, monthly_reporting_by_facility.columns.isin(facilities_with_location)]
 monthly_reporting_by_facility = monthly_reporting_by_facility[facilities_with_location]
 
-print(len(facilities_with_location))
-print(len(monthly_reporting_by_facility.columns))
-print(len(weather_df.columns))
 monthly_reporting_by_facility.to_csv("/Users/rem76/Desktop/Climate_change_health/Data/monthly_reporting_by_smaller_facility_lm.csv")
 weather_df.to_csv("/Users/rem76/Desktop/Climate_change_health/Data/historical_weather_by_smaller_facility_lm.csv")
 
@@ -120,7 +117,7 @@
     facilities_with_lat_long["Fname"].isin(facilities_with_location)
 ]
 
-additional_rows = ["Zonename", "Resid", "A105", "A109__Altitude"]
+additional_rows = ["Zonename", "Resid", "A105", "A109__Altitude", "Ftype"]
 expanded_facility_info = included_facilities_with_lat_long[["Fname"] + additional_rows]
 
 expanded_facility_info.columns = ["Fname"] + additional_rows