Upload New File

classifier.py

+# coding=utf-8
+
+import numpy as np
+import pandas as pd
+import sklearn.metrics
+from sklearn.svm import SVC
+from sklearn.neighbors import KNeighborsClassifier
+from sklearn.model_selection import train_test_split
+from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
+
+"""Reading training data"""
+train_data = pd.read_csv("TrainingData.txt", header=None)
+y = train_data[24].tolist()
+train_data = train_data.drop(24, axis=1)
+x = train_data.values.tolist()
+
+# Storing full training data before splitting
+x = np.array(x)
+y = np.array(y)
+x_train_full = x
+y_train_full = y
+
+"""Reading testing data to predict"""
+test_data = pd.read_csv("TestingData.txt", header=None)
+x_classify = test_data.values.tolist()
+
+# Splitting training data for testing algorithm
+training1_data, validation_data, target_labels, validation_target_labels = train_test_split(
+    x,
+    y,
+    test_size=0.2,
+    random_state=0
+)
+
+"""1. k nearest neighbours classifier"""
+KNN_clf = KNeighborsClassifier()
+KNN_clf.fit(training1_data, target_labels)
+KNN_results = KNN_clf.predict(validation_data)
+print("-" * 70)
+print("K Nearest Neighbours Classifier")
+print(sklearn.metrics.classification_report(KNN_results, validation_target_labels))
+
+"""2. support vector classifier"""
+SVC_clf = SVC()
+SVC_clf.fit(training1_data, target_labels)
+SVC_results = SVC_clf.predict(validation_data)
+print("-" * 70)
+print("Support Vector Classifier")
+print(sklearn.metrics.classification_report(SVC_results, validation_target_labels))
+
+"""3. Linear Discriminant Analysis"""
+lda_clf = LinearDiscriminantAnalysis()
+lda_clf.fit(training1_data, target_labels)
+lda_results = lda_clf.predict(validation_data)
+print("-" * 70)
+print("Linear Discriminant Analysis")
+print(sklearn.metrics.classification_report(lda_results, validation_target_labels))
+
+# %%
+testDF = pd.read_csv("TestingData.txt", header=None)
+testing_data = testDF.values.tolist()
+
+# %%
+
+pre = SVC_clf.predict(testing_data)
+
+pre = pd.DataFrame(pre)
+testing_data = pd.DataFrame(testing_data)
+all_result = pd.concat([testing_data, pre], axis=1)
+# print(all_result)
+
+# %%
+all_result.to_csv("TestingResults.txt", header=0, index=0)
+
+if __name__ == "__main__":
+    pass