Add performance and accuracy tests for different classifiers

classifiers_test.py

@@ -0,0 +1,70 @@
+import time
+
+import pandas as pd
+from sklearn import preprocessing
+from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis
+from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier, GradientBoostingClassifier
+from sklearn.gaussian_process import GaussianProcessClassifier
+from sklearn.gaussian_process.kernels import RBF
+from sklearn.metrics import accuracy_score
+from sklearn.naive_bayes import GaussianNB
+from sklearn.neighbors import KNeighborsClassifier
+from sklearn.neural_network import MLPClassifier
+from sklearn.svm import SVC
+from sklearn.tree import DecisionTreeClassifier
+
+
+def invoke_and_measure(func, *args, **kwargs):
+    start_time = time.time()
+    result = func(*args, **kwargs)
+    end_time = time.time()
+
+    elapsed_time = end_time - start_time
+    return result, elapsed_time
+
+data = pd.read_csv('starclusters-global-parameters2.dat',skiprows=1 ,delim_whitespace=True, header=None)
+
+shuffled_data = data.sample(frac=1, random_state=42)
+n = int(0.8 * len(shuffled_data))
+
+data_train = shuffled_data[:n]
+data_test = shuffled_data[n:]
+
+X_train = data_train.iloc[:, 1:-1].values
+y_train = data_train.iloc[:, -1].values
+
+lab = preprocessing.LabelEncoder()
+y_transformed = lab.fit_transform(y_train)
+
+X_test = data_test.iloc[:, 1:-1].values
+
+names = [
+    "Nearest Neighbors",
+    "Decision Tree",
+    "Random Forest",
+    "Neural Net",
+    "AdaBoost",
+    "Naive Bayes",
+    "QDA",
+    "SVC",
+    "Gradient Boosting"
+]
+
+classifiers = [
+    KNeighborsClassifier(3),
+    DecisionTreeClassifier(max_depth=5),
+    RandomForestClassifier(max_depth=5, n_estimators=10, max_features=1),
+    MLPClassifier(alpha=1, max_iter=1000),
+    AdaBoostClassifier(),
+    GaussianNB(),
+    QuadraticDiscriminantAnalysis(),
+    SVC(),
+    GradientBoostingClassifier()
+]
+
+
+for name, clf in zip(names, classifiers):
+    _, fit_time = invoke_and_measure(clf.fit, X_train, y_transformed)
+    y_pred, pred_time = invoke_and_measure(clf.predict, X_test)
+    accuracy = accuracy_score(lab.transform(data_test.iloc[:, -1].values), y_pred)
+    print(f"{name}: accuracy={accuracy * 100:.2f}% train={fit_time:.5f}s predict={pred_time:.5f}s")