Explore-AI · 123-BNM · May 6, 2022 · May 11, 2022 · May 11, 2022 · May 11, 2022
diff --git a/Advanced-Regression-Starter-Data/.DS_Store b/Advanced-Regression-Starter-Data/.DS_Store
diff --git a/Advanced-Regression-Starter-Data/.ipynb_checkpoints/starter-notebook-checkpoint.ipynb b/Advanced-Regression-Starter-Data/.ipynb_checkpoints/starter-notebook-checkpoint.ipynb
diff --git a/Advanced-Regression-Starter-Data/Team_CCB2.ipynb b/Advanced-Regression-Starter-Data/Team_CCB2.ipynb
diff --git a/Advanced-Regression-Starter-Data/df_test.csv b/Advanced-Regression-Starter-Data/df_test.csv
diff --git a/Advanced-Regression-Starter-Data/df_train.csv b/Advanced-Regression-Starter-Data/df_train.csv
diff --git a/Advanced-Regression-Starter-Data/submissionA.csv b/Advanced-Regression-Starter-Data/submissionA.csv
diff --git a/Advanced-Regression-Starter-Data/submissionB.csv b/Advanced-Regression-Starter-Data/submissionB.csv
diff --git a/Advanced-Regression-Starter-Data/submissionF.csv b/Advanced-Regression-Starter-Data/submissionF.csv
diff --git a/api.py b/api.py
@@ -30,7 +30,7 @@
 # Load our model into memory.
 # Please update this path to reflect your own trained model.
 static_model = load_model(
-    path_to_model='assets/trained-models/load_shortfall_simple_lm_regression.pkl')
+    path_to_model='assets/trained-models/CBB2.pkl')
 
 print ('-'*40)
 print ('Model successfully loaded')

diff --git a/assets/trained-models/CBB2.pkl b/assets/trained-models/CBB2.pkl
diff --git a/assets/trained-models/load_shortfall_simple_lm_regression.pkl b/assets/trained-models/load_shortfall_simple_lm_regression.pkl
diff --git a/model.py b/model.py
@@ -48,6 +48,8 @@ def _preprocess_data(data):
     feature_vector_dict = json.loads(data)
     # Load the dictionary as a Pandas DataFrame.
     feature_vector_df = pd.DataFrame.from_dict([feature_vector_dict])
+    new_f = ['Madrid_wind_speed', 'Bilbao_wind_deg', 'Bilbao_pressure',
+                 'Valencia_temp_min']
 
     # ---------------------------------------------------------------
     # NOTE: You will need to swap the lines below for your own data
@@ -58,7 +60,7 @@ def _preprocess_data(data):
     # ---------------------------------------------------------------
 
     # ----------- Replace this code with your own preprocessing steps --------
-    predict_vector = feature_vector_df[['Madrid_wind_speed','Bilbao_rain_1h','Valencia_wind_speed']]
+    predict_vector = feature_vector_df[new_f]
     # ------------------------------------------------------------------------
 
     return predict_vector
@@ -107,4 +109,4 @@ def make_prediction(data, model):
     # Perform prediction with model and preprocessed data.
     prediction = model.predict(prep_data)
     # Format as list for output standardisation.
-    return prediction[0].tolist()
+    return prediction[0].tolist()
diff --git a/utils/request.py b/utils/request.py
@@ -36,8 +36,8 @@
 # NOTE: When testing your instance of the API on a remote machine
 # replace the URL below with its public IP:
 
-# url = 'http://{public-ip-address-of-remote-machine}:5000/api_v0.1'
-url = 'http://127.0.0.1:5000/api_v0.1'
+url = 'http://54.91.80.97:5000/api_v0.1'
+#url = 'http://127.0.0.1:5000/api_v0.1'
 
 # Perform the POST request.
 print(f"Sending POST request to web server API at: {url}")
@@ -53,3 +53,4 @@
 print(f"API prediction result: {api_response.json()[0]}")
 print(f"The response took: {api_response.elapsed.total_seconds()} seconds")
 print("*"*50)
+
diff --git a/utils/train_model.py b/utils/train_model.py
@@ -18,14 +18,15 @@
 train = pd.read_csv('./data/df_train.csv')
 
 y_train = train[['load_shortfall_3h']]
-X_train = train[['Madrid_wind_speed','Bilbao_rain_1h','Valencia_wind_speed']]
+X_train = train[['Madrid_wind_speed', 'Bilbao_wind_deg', 'Bilbao_pressure',
+                 'Valencia_temp_min']]
 
 # Fit model
 lm_regression = LinearRegression(normalize=True)
 print ("Training Model...")
 lm_regression.fit(X_train, y_train)
 
 # Pickle model for use within our API
-save_path = '../assets/trained-models/load_shortfall_simple_lm_regression.pkl'
+save_path = '../assets/trained-models/CBB2.pkl'
 print (f"Training completed. Saving model to: {save_path}")
-pickle.dump(lm_regression, open(save_path,'wb'))
+pickle.dump(lm_regression, open(save_path,'wb'))