Merge pull request #1 from brettcannon/python-tweaks

Python tweaks

Author: negust-microsoft

samples/features/machine-learning-services/python/getting-started/rental-prediction/rental_prediction.py

@@ -1,6 +1,6 @@
-import pandas as pd
-from sklearn.linear_model import LinearRegression
-from sklearn.metrics import mean_squared_error
+import pandas
+import sklearn.linear_model
+import sklearn.metrics
 
 from revoscalepy.computecontext.RxInSqlServer import RxInSqlServer
 from revoscalepy.computecontext.RxInSqlServer import RxSqlServerData
@@ -9,43 +9,36 @@
 
 def get_rental_predictions():
     conn_str = 'Driver=SQL Server;Server=MYSQLSERVER;Database=TutorialDB;Trusted_Connection=True;'
-    column_info = { 
-            "Year" : { "type" : "integer" },
-            "Month" : { "type" : "integer" }, 
-            "Day" : { "type" : "integer" }, 
-            "RentalCount" : { "type" : "integer" }, 
-            "WeekDay" : { 
-                "type" : "factor", 
-                "levels" : ["1", "2", "3", "4", "5", "6", "7"]
-            },
-            "Holiday" : { 
-                "type" : "factor", 
-                "levels" : ["1", "0"]
-            },
-            "Snow" : { 
-                "type" : "factor", 
-                "levels" : ["1", "0"]
-            }
+    column_info = {
+        "Year": {"type": "integer"},
+        "Month": {"type": "integer"},
+        "Day": {"type": "integer"},
+        "RentalCount": {"type": "integer"},
+        "WeekDay": {
+            "type": "factor",
+            "levels": ["1", "2", "3", "4", "5", "6", "7"],
+        },
+        "Holiday": {
+            "type": "factor",
+            "levels": ["1", "0"],
+        },
+        "Snow": {
+            "type": "factor",
+            "levels": ["1", "0"],
         }
+    }
 
     data_source = RxSqlServerData(table="dbo.rental_data",
-                                  connectionString=conn_str, colInfo=column_info)
-    computeContext = RxInSqlServer(
-        connectionString = conn_str,
-        numTasks = 1,
-        autoCleanup = False
-        )
-     
-    
+                                  connectionString=conn_str,
+                                  colInfo=column_info)
     RxInSqlServer(connectionString=conn_str, numTasks=1, autoCleanup=False)
-    
+
     # import data source and convert to pandas dataframe
-    df = pd.DataFrame(rx_import_datasource(data_source))
+    df = pandas.DataFrame(rx_import_datasource(data_source))
     print("Data frame:", df)
-    # Get all the columns from the dataframe.
-    columns = df.columns.tolist()
-    # Filter the columns to remove ones we don't want.
-    columns = [c for c in columns if c not in ["Year"]]
+    # Get all the columns from the dataframe and filter out the ones we don't
+    # want.
+    columns = [x for x in df.columns if x == "Year"]
     # Store the variable we'll be predicting on.
     target = "RentalCount"
     # Generate the training set.  Set random_state to be able to replicate results.
@@ -56,14 +49,16 @@ def get_rental_predictions():
     print("Training set shape:", train.shape)
     print("Testing set shape:", test.shape)
     # Initialize the model class.
-    lin_model = LinearRegression()
+    lin_model = sklearn.linear_model.LinearRegression()
     # Fit the model to the training data.
     lin_model.fit(train[columns], train[target])
     # Generate our predictions for the test set.
     lin_predictions = lin_model.predict(test[columns])
     print("Predictions:", lin_predictions)
     # Compute error between our test predictions and the actual values.
-    lin_mse = mean_squared_error(lin_predictions, test[target])
+    lin_mse = sklearn.metrics.mean_squared_error(lin_predictions, test[target])
     print("Computed error:", lin_mse)
 
-get_rental_predictions()
+
+if __name__ == "__main__":
+    get_rental_predictions()

samples/features/machine-learning-services/python/getting-started/rental-prediction/rental_prediction.sql

@@ -27,23 +27,24 @@ BEGIN
       @language = N'Python'
     , @script = N'
 
+from sklearn import linear_model
+
+import pickle
+
+
 df = rental_train_data
 
 # Get all the columns from the dataframe.
 columns = df.columns.tolist()
 
-
 # Store the variable well be predicting on.
 target = "RentalCount"
 
-from sklearn.linear_model import LinearRegression
-
 # Initialize the model class.
-lin_model = LinearRegression()
+lin_model = linear_model.LinearRegression()
 # Fit the model to the training data.
 lin_model.fit(df[columns], df[target])
 
-import pickle
 #Before saving the model to the DB table, we need to convert it to a binary object
 trained_model = pickle.dumps(lin_model)
 '
@@ -75,15 +76,15 @@ AS
 BEGIN
 	DECLARE @py_model varbinary(max) = (select model from rental_py_models where model_name = @model);
 
-	EXEC sp_execute_external_script 
+	EXEC sp_execute_external_script
 					@language = N'Python'
 				  , @script = N'
 
 
 import pickle
 rental_model = pickle.loads(py_model)
 
-  
+
 df = rental_score_data
 #print(df)
 
@@ -106,15 +107,15 @@ lin_mse = mean_squared_error(linpredictions, df[target])
 #print(lin_mse)
 
 import pandas as pd
-predictions_df = pd.DataFrame(lin_predictions)  
+predictions_df = pd.DataFrame(lin_predictions)
 OutputDataSet = pd.concat([predictions_df, df["RentalCount"], df["Month"], df["Day"], df["WeekDay"], df["Snow"], df["Holiday"], df["Year"]], axis=1)
 '
 	, @input_data_1 = N'Select "RentalCount", "Year" ,"Month", "Day", "WeekDay", "Snow", "Holiday"  from rental_data where Year = 2015'
 	, @input_data_1_name = N'rental_score_data'
 	, @params = N'@py_model varbinary(max)'
 	, @py_model = @py_model
 	with result sets (("RentalCount_Predicted" float, "RentalCount" float, "Month" float,"Day" float,"WeekDay" float,"Snow" float,"Holiday" float, "Year" float));
-			  
+
 END;
 GO