ok

CART/Python/CART_Training.py

@@ -4,45 +4,11 @@ from sklearn.model_selection import train_test_split
 import pandas as pd
 from matplotlib import pyplot as plt
 from sklearn import tree
-from sklearn.metrics import ConfusionMatrixDisplay, confusion_matrix
+from sklearn.metrics import ConfusionMatrixDisplay, confusion_matrix, accuracy_score
 import graphviz
 from CART import CartTree
 
 
-def trainCartCropRec():
-    # Extract dataset
-    dataset = '../../DATASETS/croprec.csv'
-    crop_df = pd.read_csv(dataset, header=0)
-    Y = crop_df.label.values
-    features = crop_df.columns.values[:-1]
-    crop_df = crop_df.drop('label', axis=1)
-    X = crop_df.values
-    classes = np.unique(Y)
-
-    print(features, classes)
-    print(classes.shape)
-
-    # TRAIN/TEST SPLIT
-    X_train, X_test, Y_train, Y_test = train_test_split(
-        X, Y, test_size=0.33, random_state=42)
-    X_test, X_val, Y_test, Y_val = train_test_split(
-        X_test, Y_test, test_size=0.33, random_state=42)
-
-    X_train = np.delete(X_train, [-1, -2], axis=1)
-    X_val = np.delete(X_val, [-1, -2], axis=1)
-    new_df = pd.DataFrame(X_test)
-    files = new_df.iloc[:, -2:]
-    files.columns = ["Classes", "Paths"]
-    save_file_as_csv(files, "CART")
-    X_test = np.delete(X_test, [-1, -2], axis=1)
-
-    # My CART_TREES TREE
-    print("Training !")
-    myclassifier = CartTree(max_depth=12)
-    myclassifier.fit(X_train, Y_train)
-    print(myclassifier)
-
-
 def trainCart(comparisonSKLearn=False):
     dataset = "build/Extraction/features.csv"
     df = pd.read_csv(dataset, header=0)
@@ -62,7 +28,6 @@ def trainCart(comparisonSKLearn=False):
     files = new_df.iloc[:, -2:]
     files.columns = ["Classes", "Paths"]
     save_file_as_csv(files, "CART")
-    print("Splitting test, train", X_train.shape, X_test.shape)
 
     # My CART_TREES TREE
     print("Training !")
@@ -70,38 +35,39 @@ def trainCart(comparisonSKLearn=False):
     myclassifier.fit(X_train, Y_train)
     # Write in cpp header file CARTTrainedcpp.h
     write_model(myclassifier)
-    # Print confusion matrix
-    Y_pred = myclassifier.predict(X_test)
-    print(confusion_matrix(Y_test, Y_pred, labels=classes))
+
+    # print()
     # Comparison with SKLearn:
     if comparisonSKLearn:
         # SKLEARN CART_TREES TREE
         clf = tree.DecisionTreeClassifier(random_state=None, max_depth=12)
         clf = clf.fit(X_train, Y_train)
 
-        dot_data = tree.export_graphviz(clf,
-                                        out_file=None,
-                                        feature_names=features,
-                                        class_names=classes,
-                                        filled=True,
-                                        rounded=True,
-                                        special_characters=True)
-        graph = graphviz.Source(dot_data)
-        graph.render("rCrop recommandations")
+        # dot_data = tree.export_graphviz(clf,
+        #                                 out_file=None,
+        #                                 feature_names=features,
+        #                                 class_names=classes,
+        #                                 filled=True,
+        #                                 rounded=True,
+        #                                 special_characters=True)
+        # graph = graphviz.Source(dot_data)
+        # graph.render("rCrop recommandations")
 
         # PREDICTIONS
         Y_pred = myclassifier.predict(X_test)
+        print("accuracy :", accuracy_score(Y_test, Y_pred))
         print(confusion_matrix(Y_test, Y_pred, labels=classes))
         ConfusionMatrixDisplay.from_predictions(
             Y_test, Y_pred, display_labels=classes)
         plt.title("My predictions")
         plt.show()
 
-        Y_pred = clf.predict(X_test)
-        ConfusionMatrixDisplay.from_predictions(
-            Y_test, Y_pred, display_labels=classes)
-        plt.title("SKLEARN")
-        plt.show()
+        # Y_pred = clf.predict(X_test)
+        # print("accuracy :", accuracy_score(Y_test, Y_pred))
+        # ConfusionMatrixDisplay.from_predictions(
+        #     Y_test, Y_pred, display_labels=classes)
+        # plt.title("SKLEARN")
+        # plt.show()
 
 
 def write_model(classifier):
@@ -114,7 +80,6 @@ def write_model(classifier):
 
 
 def save_file_as_csv(data, name_folder):
-
     genres = data["Classes"].tolist()
     paths = data["Paths"].tolist()
     print(genres)
@@ -125,5 +90,4 @@ def save_file_as_csv(data, name_folder):
 
 
 if __name__ == "__main__":
-    # trainCartCropRec()
-    trainCart(False)
+    trainCart(comparisonSKLearn=True)

CART/main.cpp

@@ -9,17 +9,16 @@ int main(int argc, char **argv)
     if (argc > 1)
     {
         file_path = argv[1];
+        auto start_chrono = std::chrono::high_resolution_clock::now();
+        std::map<FTYPE, DataVector> features = compute_features_for(file_path);
+        std::string result2 = cartModel(features);
+        auto stop_chrono = std::chrono::high_resolution_clock::now();
+        auto duration = std::chrono::duration_cast<std::chrono::microseconds>(stop_chrono - start_chrono);
+        std::cout << "Predicted genre (version weight saved): " << result2 << " with " << duration.count() << " microseconds" << std::endl;
     }
-    else
-    {
-        file_path = "/home/hugo/Documents/embedded-machine-learning/DATASETS/genres/disco/disco.00010.au";
-    }
-    std::map<FTYPE, DataVector> features = compute_features_for(file_path);
-    std::string result = cartModel(features);
     std::cout << "Compute accuracy... \n";
     real accuracy = compute_accuracy_CART("/home/hugo/Documents/embedded-machine-learning/CART/file_test.csv", (vFunctionCallCART)cartModel, matrix);
     std::cout << "Accuracy: " << accuracy << "\n";
-    std::cout << result << std::endl;
     std::cout << "Confusion matrix: \n";
     print_2D_array(matrix);
     return 0;