Format TMVA SOFIE tutorial code

User-facing code like tutorials should be nicely formatted, in
particular avoiding non-standard indentations with three spaces that can
annoy users when copy-pasting code.

Author: guitargeek

tutorials/machine_learning/TMVA_SOFIE_Keras.py

@@ -9,7 +9,6 @@
 ### \author Sanjiban Sengupta and Lorenzo Moneta
 
 
-
 import ROOT
 
 # Enable ROOT in batch mode (same effect as -nodraw)
@@ -23,22 +22,22 @@
 from tensorflow.keras.layers import Activation, Dense, Input, Softmax
 from tensorflow.keras.models import Model
 
-input=Input(shape=(4,),batch_size=2)
-x=Dense(32)(input)
-x=Activation('relu')(x)
-x=Dense(16,activation='relu')(x)
-x=Dense(8,activation='relu')(x)
-x=Dense(2)(x)
-output=Softmax()(x)
-model=Model(inputs=input,outputs=output)
+input = Input(shape=(4,), batch_size=2)
+x = Dense(32)(input)
+x = Activation("relu")(x)
+x = Dense(16, activation="relu")(x)
+x = Dense(8, activation="relu")(x)
+x = Dense(2)(x)
+output = Softmax()(x)
+model = Model(inputs=input, outputs=output)
 
-randomGenerator=np.random.RandomState(0)
-x_train=randomGenerator.rand(4,4)
-y_train=randomGenerator.rand(4,2)
+randomGenerator = np.random.RandomState(0)
+x_train = randomGenerator.rand(4, 4)
+y_train = randomGenerator.rand(4, 2)
 
-model.compile(loss='mse', optimizer='adam')
+model.compile(loss="mse", optimizer="adam")
 model.fit(x_train, y_train, epochs=3, batch_size=2)
-model.save('KerasModel.keras')
+model.save("KerasModel.keras")
 model.summary()
 
 # -----------------------------------------------------------------------------
@@ -54,7 +53,7 @@
 # Generate inference code
 model.Generate()
 model.OutputGenerated()
-#print generated code
+# print generated code
 print("\n**************************************************")
 print("           Generated code")
 print("**************************************************\n")
@@ -69,14 +68,13 @@
 # Step 3: Run inference
 # -----------------------------------------------------------------------------
 
-#instantiate SOFIE session class
+# instantiate SOFIE session class
 session = ROOT.TMVA_SOFIE_KerasModel.Session()
 
 # Input tensor (same shape as training input)
-x = np.array([[0.1, 0.2, 0.3, 0.4],[0.5, 0.6, 0.7, 0.8]], dtype=np.float32)
+x = np.array([[0.1, 0.2, 0.3, 0.4], [0.5, 0.6, 0.7, 0.8]], dtype=np.float32)
 
 # Run inference
 y = session.infer(x)
 
 print("Inference output:", y)
-

tutorials/machine_learning/TMVA_SOFIE_Keras_HiggsModel.py

@@ -16,82 +16,85 @@
 from sklearn.model_selection import train_test_split
 
 
-def CreateModel(nlayers = 4, nunits = 64):
-   input = layers.Input(shape=(7,))
-   x = input
-   for i in range(1,nlayers) :
-      y = layers.Dense(nunits, activation='relu')(x)
-      x = y
+def CreateModel(nlayers=4, nunits=64):
+    input = layers.Input(shape=(7,))
+    x = input
+    for i in range(1, nlayers):
+        y = layers.Dense(nunits, activation="relu")(x)
+        x = y
 
-   output = layers.Dense(1, activation='sigmoid')(x)
-   model = models.Model(input, output)
-   model.compile(loss = 'binary_crossentropy', optimizer = 'adam', weighted_metrics = ['accuracy'])
-   model.summary()
-   return model
+    output = layers.Dense(1, activation="sigmoid")(x)
+    model = models.Model(input, output)
+    model.compile(loss="binary_crossentropy", optimizer="adam", weighted_metrics=["accuracy"])
+    model.summary()
+    return model
 
-def PrepareData() :
-   #get the input data
-   inputFile = str(ROOT.gROOT.GetTutorialDir()) + "/machine_learning/data/Higgs_data.root"
 
-   df1 = ROOT.RDataFrame("sig_tree", inputFile)
-   sigData = df1.AsNumpy(columns=['m_jj', 'm_jjj', 'm_lv', 'm_jlv', 'm_bb', 'm_wbb', 'm_wwbb'])
-   #print(sigData)
+def PrepareData():
+    # get the input data
+    inputFile = str(ROOT.gROOT.GetTutorialDir()) + "/machine_learning/data/Higgs_data.root"
 
-   # stack all the 7 numpy array in a single array (nevents x nvars)
-   xsig = np.column_stack(list(sigData.values()))
-   data_sig_size = xsig.shape[0]
-   print("size of data", data_sig_size)
+    df1 = ROOT.RDataFrame("sig_tree", inputFile)
+    sigData = df1.AsNumpy(columns=["m_jj", "m_jjj", "m_lv", "m_jlv", "m_bb", "m_wbb", "m_wwbb"])
+    # print(sigData)
 
-   # make SOFIE inference on background data
-   df2 = ROOT.RDataFrame("bkg_tree", inputFile)
-   bkgData = df2.AsNumpy(columns=['m_jj', 'm_jjj', 'm_lv', 'm_jlv', 'm_bb', 'm_wbb', 'm_wwbb'])
-   xbkg = np.column_stack(list(bkgData.values()))
-   data_bkg_size = xbkg.shape[0]
+    # stack all the 7 numpy array in a single array (nevents x nvars)
+    xsig = np.column_stack(list(sigData.values()))
+    data_sig_size = xsig.shape[0]
+    print("size of data", data_sig_size)
 
-   ysig = np.ones(data_sig_size)
-   ybkg = np.zeros(data_bkg_size)
-   inputs_data = np.concatenate((xsig,xbkg),axis=0)
-   inputs_targets = np.concatenate((ysig,ybkg),axis=0)
+    # make SOFIE inference on background data
+    df2 = ROOT.RDataFrame("bkg_tree", inputFile)
+    bkgData = df2.AsNumpy(columns=["m_jj", "m_jjj", "m_lv", "m_jlv", "m_bb", "m_wbb", "m_wwbb"])
+    xbkg = np.column_stack(list(bkgData.values()))
+    data_bkg_size = xbkg.shape[0]
 
-   #split data in training and test data
+    ysig = np.ones(data_sig_size)
+    ybkg = np.zeros(data_bkg_size)
+    inputs_data = np.concatenate((xsig, xbkg), axis=0)
+    inputs_targets = np.concatenate((ysig, ybkg), axis=0)
 
-   x_train, x_test, y_train, y_test = train_test_split(
-        inputs_data, inputs_targets, test_size=0.50, random_state=1234)
+    # split data in training and test data
 
-   return x_train, y_train, x_test, y_test
+    x_train, x_test, y_train, y_test = train_test_split(inputs_data, inputs_targets, test_size=0.50, random_state=1234)
 
-def TrainModel(model, x, y, name) :
-   model.fit(x,y,epochs=5,batch_size=50)
-   modelFile = name + '.keras'
-   model.save(modelFile)
-   return model, modelFile
+    return x_train, y_train, x_test, y_test
 
 
-def  GenerateCode(modelFile = "model.keras") :
+def TrainModel(model, x, y, name):
+    model.fit(x, y, epochs=5, batch_size=50)
+    modelFile = name + ".keras"
+    model.save(modelFile)
+    return model, modelFile
 
-   #check if the input file exists
-   if not exists(modelFile):
-      raise FileNotFoundError("INput model file not existing. You need to run TMVA_Higgs_Classification.C to generate the Keras trained model")
 
+def GenerateCode(modelFile="model.keras"):
 
-   #parse the input Keras model into RModel object (force batch size to be 1)
-   model = ROOT.TMVA.Experimental.SOFIE.PyKeras.Parse(modelFile)
+    # check if the input file exists
+    if not exists(modelFile):
+        raise FileNotFoundError(
+            "INput model file not existing. You need to run TMVA_Higgs_Classification.C to generate the Keras trained model"
+        )
 
-   #Generating inference code
-   model.Generate()
-   model.OutputGenerated()
+    # parse the input Keras model into RModel object (force batch size to be 1)
+    model = ROOT.TMVA.Experimental.SOFIE.PyKeras.Parse(modelFile)
+
+    # Generating inference code
+    model.Generate()
+    model.OutputGenerated()
+
+    modelName = modelFile.replace(".keras", "")
+    return modelName
 
-   modelName = modelFile.replace(".keras","")
-   return modelName
 
 ###################################################################
 ## Step 1 : Create and Train model
 ###################################################################
 
 x_train, y_train, x_test, y_test = PrepareData()
-#create dense model with 3 layers of 64 units
-model = CreateModel(3,64)
-model, modelFile = TrainModel(model,x_train, y_train, 'HiggsModel')
+# create dense model with 3 layers of 64 units
+model = CreateModel(3, 64)
+model, modelFile = TrainModel(model, x_train, y_train, "HiggsModel")
 
 ###################################################################
 ## Step 2 : Parse model and generate inference code with SOFIE
@@ -110,20 +113,17 @@ def  GenerateCode(modelFile = "model.keras") :
 ## Step 4: Evaluate the model
 ###################################################################
 
-#get first the SOFIE session namespace
-sofie = getattr(ROOT, 'TMVA_SOFIE_' + modelName)
+# get first the SOFIE session namespace
+sofie = getattr(ROOT, "TMVA_SOFIE_" + modelName)
 session = sofie.Session()
 
-x = np.random.normal(0,1,7).astype(np.float32)
+x = np.random.normal(0, 1, 7).astype(np.float32)
 y = session.infer(x)
-ykeras = model(x.reshape(1,7)).numpy()
+ykeras = model(x.reshape(1, 7)).numpy()
 
-print("input to model is ",x, "\n\t -> output using SOFIE = ", y[0], " using Keras = ", ykeras[0])
+print("input to model is ", x, "\n\t -> output using SOFIE = ", y[0], " using Keras = ", ykeras[0])
 
-if (abs(y[0]-ykeras[0]) > 0.01) :
-   raise RuntimeError('ERROR: Result is different between SOFIE and Keras')
+if abs(y[0] - ykeras[0]) > 0.01:
+    raise RuntimeError("ERROR: Result is different between SOFIE and Keras")
 
 print("OK")
-
-
-