Use idiomatic Python and fix formatting

Misc/PythonSQL/DeserializeSavePlots.py

@@ -1,12 +1,13 @@
 import pyodbc
 import pickle
 import os
+
 cnxn = pyodbc.connect('DRIVER={SQL Server};SERVER={SERVER_NAME};DATABASE={DB_NAME};UID={USER_NAME};PWD={PASSWORD}')
 cursor = cnxn.cursor()
 cursor.execute("EXECUTE [dbo].[SerializePlots]")
 tables = cursor.fetchall()
-for i in range(0, len(tables)):
-    fig = pickle.loads(tables[i][0])
-    fig.savefig(str(i)+'.png');
+for i, table in enumerate(tables):
+    fig = pickle.loads(table[0])
+    fig.savefig(str(i)+'.png')
 
-print("The plots are saved in directory: ",os.getcwd())
+print("The plots are saved in directory:", os.getcwd())

Misc/PythonSQL/DeserializeSavePlots2.py

@@ -1,12 +1,13 @@
 import pyodbc
 import pickle
 import os
+
 cnxn = pyodbc.connect('DRIVER={SQL Server};SERVER={SERVER_NAME};DATABASE={DB_NAME};Trusted_Connection=yes;')
 cursor = cnxn.cursor()
 cursor.execute("EXECUTE [dbo].[SerializePlots]")
 tables = cursor.fetchall()
-for i in range(0, len(tables)):
-    fig = pickle.loads(tables[i][0])
+for i, table in enumerate(tables):
+    fig = pickle.loads(table[0])
     fig.savefig(str(i)+'.png')
 
-print("The plots are saved in directory: ",os.getcwd())
+print("The plots are saved in directory:", os.getcwd())

Misc/PythonSQL/PredictTipRxPy.sql

@@ -20,26 +20,24 @@ BEGIN
   EXEC sp_execute_external_script 
 	@language = N'Python',
     @script = N'
-import pickle;
-import numpy;
-import pandas;
+import pickle
+import numpy
+import pandas
 from sklearn import metrics
-from revoscalepy.functions.RxPredict import rx_predict_ex;
+from revoscalepy.functions.RxPredict import rx_predict_ex
 
 mod = pickle.loads(lmodel2)
 X = InputDataSet[["passenger_count", "trip_distance", "trip_time_in_secs", "direct_distance"]]
 y = numpy.ravel(InputDataSet[["tipped"]])
 
-probArray = rx_predict_ex(mod, X)
-probList = []
-for i in range(len(probArray._results["tipped_Pred"])):
-	probList.append((probArray._results["tipped_Pred"][i]))
+prob_array = rx_predict_ex(mod, X)
+prob_list = list(prob_rrray._results["tipped_Pred"])
 
-probArray = numpy.asarray(probList)
-fpr, tpr, thresholds = metrics.roc_curve(y, probArray)
-aucResult = metrics.auc(fpr, tpr)
-print ("AUC on testing data is: " + str(aucResult))
-OutputDataSet = pandas.DataFrame(data = probList, columns = ["predictions"])
+prob_array = numpy.asarray(prob_list)
+fpr, tpr, thresholds = metrics.roc_curve(y, prob_array)
+auc_result = metrics.auc(fpr, tpr)
+print("AUC on testing data is:", auc_result)
+OutputDataSet = pandas.DataFrame(data=prob_list, columns=["predictions"])
 ',	
 	@input_data_1 = @inquery,
 	@input_data_1_name = N'InputDataSet',

Misc/PythonSQL/PredictTipSciKitPy.sql

@@ -21,27 +21,25 @@ BEGIN
   EXEC sp_execute_external_script 
 	@language = N'Python',
     @script = N'
-import pickle;
-import numpy;
-import pandas;
+import pickle
+import numpy
+import pandas
 from sklearn import metrics
 
 mod = pickle.loads(lmodel2)
 
 X = InputDataSet[["passenger_count", "trip_distance", "trip_time_in_secs", "direct_distance"]]
 y = numpy.ravel(InputDataSet[["tipped"]])
 
-probArray = mod.predict_proba(X)
-probList = []
-for i in range(len(probArray)):
-	probList.append((probArray[i])[1])
+prob_array = mod.predict_proba(X)
+prob_list = [item[1] for item in prob_array]
 
-probArray = numpy.asarray(probList)
-fpr, tpr, thresholds = metrics.roc_curve(y, probArray)
-aucResult = metrics.auc(fpr, tpr)
-print ("AUC on testing data is: " + str(aucResult))
+prob_array = numpy.asarray(prob_list)
+fpr, tpr, thresholds = metrics.roc_curve(y, prob_array)
+auc_result = metrics.auc(fpr, tpr)
+print("AUC on testing data is:", auc_result)
 
-OutputDataSet = pandas.DataFrame(data = probList, columns = ["predictions"])
+OutputDataSet = pandas.DataFrame(data=prob_list, columns=["predictions"])
 ',	
 	@input_data_1 = @inquery,
 	@input_data_1_name = N'InputDataSet',

Misc/PythonSQL/PredictTipSingleModeRxPy.sql

@@ -31,26 +31,25 @@ BEGIN
 	EXEC sp_execute_external_script 
 		@language = N'Python',
 		@script = N'
-import pickle;
-import numpy;
-import pandas;
-from revoscalepy.functions.RxPredict import rx_predict_ex;
+import pickle
+import numpy
+import pandas
+from revoscalepy.functions.RxPredict import rx_predict_ex
 
 # Load model and unserialize
 mod = pickle.loads(model)
 
 # Get features for scoring from input data
-X = InputDataSet[["passenger_count", "trip_distance", "trip_time_in_secs", "direct_distance"]]
+x = InputDataSet[["passenger_count", "trip_distance", "trip_time_in_secs", "direct_distance"]]
 
 # Score data to get tip prediction probability as a list (of float)
 
-probArray = rx_predict_ex(mod, X)
+prob_array = rx_predict_ex(mod, x)
 
-probList = []
-probList.append(probArray._results["tipped_Pred"])
+prob_list = [prob_array._results["tipped_Pred"]]
 
 # Create output data frame
-OutputDataSet = pandas.DataFrame(data = probList, columns = ["predictions"])
+OutputDataSet = pandas.DataFrame(data=prob_list, columns=["predictions"])
 	',
 	@input_data_1 = @inquery,
 	@params = N'@model varbinary(max),@passenger_count int,@trip_distance float,

Misc/PythonSQL/PredictTipSingleModeSciKitPy.sql

@@ -31,9 +31,9 @@ BEGIN
 	EXEC sp_execute_external_script 
 		@language = N'Python',
 		@script = N'
-import pickle;
-import numpy;
-import pandas;
+import pickle
+import numpy
+import pandas
 
 # Load model and unserialize
 mod = pickle.loads(model)
@@ -42,11 +42,10 @@ mod = pickle.loads(model)
 X = InputDataSet[["passenger_count", "trip_distance", "trip_time_in_secs", "direct_distance"]]
 
 # Score data to get tip prediction probability as a list (of float)
-probList = []
-probList.append((mod.predict_proba(X)[0])[1])
+prob = [mod.predict_proba(X)[0][1]]
 
 # Create output data frame
-OutputDataSet = pandas.DataFrame(data = probList, columns = ["predictions"])
+OutputDataSet = pandas.DataFrame(data=prob, columns=["predictions"])
 	',
 	@input_data_1 = @inquery,
 	@params = N'@model varbinary(max),@passenger_count int,@trip_distance float,

Misc/PythonSQL/SerializePlots.sql

@@ -27,28 +27,28 @@ plt.hist(InputDataSet.tipped)
 plt.xlabel("Tipped")
 plt.ylabel("Counts")
 plt.title("Histogram, Tipped")
-plot0 = pd.DataFrame(data =[pickle.dumps(fig_handle)], columns =["plot"])
+plot0 = pd.DataFrame(data =[pickle.dumps(fig_handle)], columns=["plot"])
 plt.clf()
 
 plt.hist(InputDataSet.tip_amount)
 plt.xlabel("Tip amount ($)")
 plt.ylabel("Counts")
 plt.title("Histogram, Tip amount")
-plot1 = pd.DataFrame(data =[pickle.dumps(fig_handle)], columns =["plot"])
+plot1 = pd.DataFrame(data =[pickle.dumps(fig_handle)], columns=["plot"])
 plt.clf()
 
 plt.hist(InputDataSet.fare_amount)
 plt.xlabel("Fare amount ($)")
 plt.ylabel("Counts")
 plt.title("Histogram, Fare amount")
-plot2 = pd.DataFrame(data =[pickle.dumps(fig_handle)], columns =["plot"])
+plot2 = pd.DataFrame(data =[pickle.dumps(fig_handle)], columns=["plot"])
 plt.clf()
 
 plt.scatter( InputDataSet.fare_amount, InputDataSet.tip_amount)
 plt.xlabel("Fare Amount ($)")
 plt.ylabel("Tip Amount ($)")
 plt.title("Tip amount by Fare amount")
-plot3 = pd.DataFrame(data =[pickle.dumps(fig_handle)], columns =["plot"])
+plot3 = pd.DataFrame(data =[pickle.dumps(fig_handle)], columns=["plot"])
 plt.clf()
 
 OutputDataSet = plot0.append(plot1, ignore_index=True).append(plot2, ignore_index=True).append(plot3, ignore_index=True)

Misc/PythonSQL/TrainTipPredictionModelRxPy.sql

@@ -21,10 +21,10 @@ BEGIN
 import numpy
 import pickle
 import pandas
-from revoscalepy.functions.RxLogit import rx_logit_ex;
-from revoscalepy.functions.RxPredict import rx_predict_ex;
+from revoscalepy.functions.RxLogit import rx_logit_ex
+from revoscalepy.functions.RxPredict import rx_predict_ex
 
-logitObj = rx_logit_ex("tipped ~ passenger_count + trip_distance + trip_time_in_secs + direct_distance", data = InputDataSet);
+logitObj = rx_logit_ex("tipped ~ passenger_count + trip_distance + trip_time_in_secs + direct_distance", data=InputDataSet);
 
 ## Serialize model
 trained_model = pickle.dumps(logitObj)