Merge pull request #37 from intel/bbela/resolve_formatting_issues

Correct formatting issues in the code

Author: kekaczma

MLOps_Professional/lab1/sample/data_model.py

@@ -1,4 +1,5 @@
 from pydantic import BaseModel
 
+
 class MaintenancePayload(BaseModel):
-    temperature: int
+    temperature: int

MLOps_Professional/lab1/sample/maintenance.py

@@ -1,6 +1,6 @@
 # maitnenace test business logic
 
-def test_maintenance(temperature:int):
+def test_maintenance(temperature: int):
     """_summary_
 
     Parameters
@@ -14,5 +14,5 @@ def test_maintenance(temperature:int):
         'Approved' or 'Denied' based on temperature readings
     """
     maintenance_status = 'Needs Maintenance' if temperature > 50 else 'No Maintenance Required'
-    
-    return maintenance_status
+
+    return maintenance_status

MLOps_Professional/lab1/sample/serve.py

@@ -23,13 +23,14 @@ async def ping():
     API response
         response from server on health status
     """
-    return {"message":"Server is Running"}
+    return {"message": "Server is Running"}
+
 
 @app.post("/maintenance")
-async def predict(payload:MaintenancePayload):
-    
+async def predict(payload: MaintenancePayload):
+
     maintenance_result = test_maintenance(payload.temperature)
     return {"msg": "Completed Analysis", "Maintenance Status": maintenance_result}
 
 if __name__ == "__main__":
-    uvicorn.run("serve:app", host="0.0.0.0", port=5000, log_level="info")
+    uvicorn.run("serve:app", host="0.0.0.0", port=5000, log_level="info")

MLOps_Professional/lab3/sample/data_model.py

@@ -1,12 +1,12 @@
 from pydantic import BaseModel
- 
+
+
 class TrainPayload(BaseModel):
     file: str
     model_name: str
     model_path: str
-    test_size: int = 25  
-    ncpu: int = 4 
+    test_size: int = 25
+    ncpu: int = 4
     mlflow_tracking_uri: str
     mlflow_new_experiment: str = None
     mlflow_experiment: str = None
-    

MLOps_Professional/lab3/sample/generate_data.py

@@ -96,12 +96,12 @@
 data.drop('Temp_Var', axis=1, inplace=True)
 
 Categorical_Variables = pd.get_dummies(
-                           data[[
-                               'Manufacturer',
-                               'Generation',
-                               'Lubrication',
-                               'Product_Assignment']],
-                           drop_first=False)
+    data[[
+        'Manufacturer',
+        'Generation',
+        'Lubrication',
+        'Product_Assignment']],
+    drop_first=False)
 data = pd.concat([data, Categorical_Variables], axis=1)
 data.drop(['Manufacturer', 'Generation', 'Lubrication', 'Product_Assignment'], axis=1, inplace=True)
 

MLOps_Professional/lab3/sample/serve.py

@@ -22,10 +22,11 @@ async def ping():
     API response
         response from server on health status
     """
-    return {"message":"Server is Running"}
+    return {"message": "Server is Running"}
+
 
 @app.post("/train")
-async def train(payload:TrainPayload):
+async def train(payload: TrainPayload):
     """Training Endpoint
     This endpoint process raw data and trains an XGBoost Classifier
 
@@ -40,9 +41,9 @@ async def train(payload:TrainPayload):
         Accuracy metrics and other logger feedback on training progress.
     """
     model = HarvesterMaintenance(payload.model_name)
-    model.mlflow_tracking(tracking_uri=payload.mlflow_tracking_uri, 
+    model.mlflow_tracking(tracking_uri=payload.mlflow_tracking_uri,
                           new_experiment=payload.mlflow_new_experiment,
-                          experiment= payload.mlflow_experiment)
+                          experiment=payload.mlflow_experiment)
     logger.info("Configured Experiment and Tracking URI for MLFlow")
     model.process_data(payload.file, payload.test_size)
     logger.info("Data has been successfully processed")
@@ -54,4 +55,4 @@ async def train(payload:TrainPayload):
     return {"msg": "Model trained succesfully", "validation scores": accuracy_score}
 
 if __name__ == "__main__":
-    uvicorn.run("serve:app", host="0.0.0.0", port=5000, log_level="info")
+    uvicorn.run("serve:app", host="0.0.0.0", port=5000, log_level="info")

MLOps_Professional/lab3/sample/train.py

@@ -10,7 +10,7 @@
 
 import numpy as np
 import xgboost as xgb
-import pandas as pd 
+import pandas as pd
 
 from sklearn.model_selection import train_test_split
 from sklearn.preprocessing import RobustScaler
@@ -24,7 +24,7 @@
 
 
 class HarvesterMaintenance():
-    
+
     def __init__(self, model_name: str):
         self.model_name = model_name
         self.file = ''
@@ -39,21 +39,21 @@ def __init__(self, model_name: str):
         self.run_id = ''
         self.active_experiment = ''
         self.xgb_model = ''
-        
+
     def mlflow_tracking(self, tracking_uri: str = './mlruns', experiment: str = None, new_experiment: str = None):
-        
+
         # sets tracking URI
         mlflow.set_tracking_uri(tracking_uri)
-        
+
         # creates new experiment if no experiment is specified
-        if experiment == None:
+        if experiment is None:
             mlflow.create_experiment(new_experiment)
             self.active_experiment = new_experiment
             mlflow.set_experiment(new_experiment)
         else:
             mlflow.set_experiment(experiment)
             self.active_experiment = experiment
-        
+
     def process_data(self, file: str, test_size: int = .25):
         """processes raw data for training
 
@@ -72,11 +72,11 @@ def process_data(self, file: str, test_size: int = .25):
         except FileNotFoundError:
             sys.exit('Dataset file not found')
 
-
         X = data.drop('Asset_Label', axis=1)
         y = data.Asset_Label
 
-        X_train, X_test, self.y_train, self.y_test = train_test_split(X, y, test_size=test_size)
+        X_train, X_test, self.y_train, self.y_test = train_test_split(
+            X, y, test_size=test_size)
 
         df_num_train = X_train.select_dtypes(['float', 'int', 'int32'])
         df_num_test = X_test.select_dtypes(['float', 'int', 'int32'])
@@ -97,21 +97,24 @@ def process_data(self, file: str, test_size: int = .25):
         del X_test_scaled_transformed['Number_Repairs']
 
         # Dropping the unscaled numerical columns
-        X_train = X_train.drop(['Age', 'Temperature', 'Last_Maintenance', 'Motor_Current'], axis=1)
-        X_test = X_test.drop(['Age', 'Temperature', 'Last_Maintenance', 'Motor_Current'], axis=1)
-        
+        X_train = X_train.drop(
+            ['Age', 'Temperature', 'Last_Maintenance', 'Motor_Current'], axis=1)
+        X_test = X_test.drop(
+            ['Age', 'Temperature', 'Last_Maintenance', 'Motor_Current'], axis=1)
+
         X_train = X_train.astype(int)
         X_test = X_test.astype(int)
 
         # Creating train and test data with scaled numerical columns
-        X_train_scaled_transformed = pd.concat([X_train_scaled_transformed, X_train], axis=1)
-        X_test_scaled_transformed = pd.concat([X_test_scaled_transformed, X_test], axis=1)
+        X_train_scaled_transformed = pd.concat(
+            [X_train_scaled_transformed, X_train], axis=1)
+        X_test_scaled_transformed = pd.concat(
+            [X_test_scaled_transformed, X_test], axis=1)
 
         self.X_train_scaled_transformed = X_train_scaled_transformed.astype(
-                                        {'Motor_Current': 'float64'})
+            {'Motor_Current': 'float64'})
         self.X_test_scaled_transformed = X_test_scaled_transformed.astype(
-                                        {'Motor_Current': 'float64'})
-        
+            {'Motor_Current': 'float64'})
 
     def train(self, ncpu: int = 4):
         """trains an XGBoost Classifier and Tracks Models with MLFlow
@@ -121,28 +124,29 @@ def train(self, ncpu: int = 4):
         ncpu : int, optional
             number of CPU threads used for training, by default 4
         """
-        
+
         # Set xgboost parameters
         self.parameters = {
-        'max_bin': 256,
-        'scale_pos_weight': 2,
-        'lambda_l2': 1,
-        'alpha': 0.9,
-        'max_depth': 8,
-        'num_leaves': 2**8,
-        'verbosity': 0,
-        'objective': 'multi:softmax',
-        'learning_rate': 0.3,
-        'num_class': 3,
-        'nthread': ncpu
+            'max_bin': 256,
+            'scale_pos_weight': 2,
+            'lambda_l2': 1,
+            'alpha': 0.9,
+            'max_depth': 8,
+            'num_leaves': 2**8,
+            'verbosity': 0,
+            'objective': 'multi:softmax',
+            'learning_rate': 0.3,
+            'num_class': 3,
+            'nthread': ncpu
         }
-        
+
         with mlflow.start_run() as run:
-            mlflow.xgboost.autolog()   
-            xgb_train = xgb.DMatrix(self.X_train_scaled_transformed, label=np.array(self.y_train))
-                      
-        self.xgb_model = xgb.train(self.parameters, xgb_train, num_boost_round=100)
-        
+            mlflow.xgboost.autolog()
+            xgb_train = xgb.DMatrix(
+                self.X_train_scaled_transformed, label=np.array(self.y_train))
+
+        self.xgb_model = xgb.train(
+            self.parameters, xgb_train, num_boost_round=100)
 
     def validate(self):
         """performs model validation with testing data
@@ -154,17 +158,20 @@ def validate(self):
         """
         dtest = xgb.DMatrix(self.X_test_scaled_transformed, self.y_test)
         xgb_prediction = self.xgb_model.predict(dtest)
-        xgb_errors_count = np.count_nonzero(xgb_prediction - np.ravel(self.y_test))
+        xgb_errors_count = np.count_nonzero(
+            xgb_prediction - np.ravel(self.y_test))
         self.accuracy_scr = 1 - xgb_errors_count / xgb_prediction.shape[0]
-        
-        xp = mlflow.get_experiment_by_name(self.active_experiment)._experiment_id
-        self.run_id = mlflow.search_runs(xp, output_format="list")[0].info.run_id
-        
-        with mlflow.start_run(self.run_id ):
-            mlflow.log_metric("accuracy",self.accuracy_scr)
-        
+
+        xp = mlflow.get_experiment_by_name(
+            self.active_experiment)._experiment_id
+        self.run_id = mlflow.search_runs(
+            xp, output_format="list")[0].info.run_id
+
+        with mlflow.start_run(self.run_id):
+            mlflow.log_metric("accuracy", self.accuracy_scr)
+
         return self.accuracy_scr
-    
+
     def save(self, model_path):
         """saves trained model to path
 
@@ -174,13 +181,13 @@ def save(self, model_path):
             path where trained model should be saved
         """
 
-        self.model_path = model_path +  self.model_name + '.joblib'
-        self.scaler_path = model_path +  self.model_name + '_scaler.joblib'
-        
+        self.model_path = model_path + self.model_name + '.joblib'
+        self.scaler_path = model_path + self.model_name + '_scaler.joblib'
+
         logger.info("Saving model")
-        with open( self.model_path, "wb") as fh:
+        with open(self.model_path, "wb") as fh:
             joblib.dump(self.xgb_model, fh.name)
-        
+
         logger.info("Saving Scaler")
-        with open( self.scaler_path, "wb") as fh:
+        with open(self.scaler_path, "wb") as fh:
             joblib.dump(self.robust_scaler, fh.name)

MLOps_Professional/lab4/sample/data_model.py

@@ -1,19 +1,21 @@
 from pydantic import BaseModel
- 
+
+
 class TrainPayload(BaseModel):
     file: str
     model_name: str
     model_path: str
-    test_size: int = 25  
-    ncpu: int = 4 
+    test_size: int = 25
+    ncpu: int = 4
     mlflow_tracking_uri: str
     mlflow_new_experiment: str = None
     mlflow_experiment: str = None
 
+
 class PredictionPayload(BaseModel):
     model_name: str
     stage: str
     sample: list
     model_run_id: str
     scaler_file_name: str
-    scaler_destination: str = './'
+    scaler_destination: str = './'

MLOps_Professional/lab4/sample/generate_data.py

@@ -96,12 +96,12 @@
 data.drop('Temp_Var', axis=1, inplace=True)
 
 Categorical_Variables = pd.get_dummies(
-                           data[[
-                               'Manufacturer',
-                               'Generation',
-                               'Lubrication',
-                               'Product_Assignment']],
-                           drop_first=False)
+    data[[
+        'Manufacturer',
+        'Generation',
+        'Lubrication',
+        'Product_Assignment']],
+    drop_first=False)
 data = pd.concat([data, Categorical_Variables], axis=1)
 data.drop(['Manufacturer', 'Generation', 'Lubrication', 'Product_Assignment'], axis=1, inplace=True)