Upload New File

task1.py

+# Importing libraries
+import matplotlib.pyplot as plt
+import pandas as pd
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import accuracy_score
+from sklearn.svm import SVC
+from sklearn.preprocessing import StandardScaler
+# Using pandas, reads a CSV file named "TrainingDataBinary.csv" and stores it in a dataframe named df.
+df = pd.read_csv("TrainingDataBinary.csv")
+# Data preprocessing: Separating features and target variable
+X = df.iloc[:, :-1]
+y = df.iloc[:, -1]
+# Data splitting and model training
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+# Feature scaling
+scaler = StandardScaler()
+X_train_scaled = scaler.fit_transform(X_train)
+X_test_scaled = scaler.transform(X_test)
+# Support Vector Classifier (SVC) initialization and training
+svc = SVC(kernel='rbf', C=10.0, gamma=0.1, random_state=42)
+# Prediction on the scaled test data
+svc.fit(X_train_scaled, y_train)
+y_pred = svc.predict(X_test_scaled)
+# Calculate and print accuracy
+accuracy = accuracy_score(y_test, y_pred)
+print("Accuracy:", accuracy)
+# Calculate and print prediction error
+prediction_error = 1 - accuracy
+print("Prediction Error:", prediction_error)
+# Plotting the scatter plot
+plt.scatter(X_test.iloc[:, 0], X_test.iloc[:, 1], c=y_pred, cmap='viridis')
+plt.xlabel("Feature 1")
+plt.ylabel("Feature 2")
+plt.title("Scatter Plot with Predicted Classes")
+plt.show()
+testingData = pd.read_csv("TestingDataBinary.csv")
+predicted = svc.predict(testingData)
+# Ensure the number of rows matches
+resultData = pd.DataFrame(predicted, columns=['PredictedMarker'])
+resultData = resultData[:testingData.shape[0]]
+# Adding predicted markers to testing data
+testingData['PredictedMarker'] = resultData["PredictedMarker"].tolist()
+# Saving the predictions to a CSV file
+testingData.to_csv("TestingResultsBinary.csv", index=False)
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+