files for comp3217 lab

3217-classification-lr-example1.py

+#Taken from Scikit
+
+import matplotlib.pyplot as plt
+from sklearn.linear_model import LogisticRegression
+from sklearn import datasets
+from sklearn.inspection import DecisionBoundaryDisplay
+
+# import some data from a predefined datatset
+iris = datasets.load_iris()
+X = iris.data[:, :2]  # we only take the first two features.
+Y = iris.target
+#print shape of the array for X and Y. Also get value of targets
+print (X.shape)
+print (Y)
+print (Y.shape)
+
+
+# Create an instance of Logistic Regression Classifier and fit the data.
+logreg = LogisticRegression(C=1)
+logreg.fit(X, Y)
+
+_, ax = plt.subplots(figsize=(4, 3))
+DecisionBoundaryDisplay.from_estimator(
+    logreg,
+    X,
+    cmap=plt.cm.Paired,
+    ax=ax,
+    response_method="auto",
+    plot_method="pcolormesh",
+    shading="auto",
+    xlabel="Sepal length",
+    ylabel="Sepal width",
+    eps=0.5,
+)
+
+# Plot the training points
+plt.scatter(X[:, 0], X[:, 1], c=Y, edgecolors="k", cmap=plt.cm.Paired)
+
+
+plt.xticks(())
+plt.yticks(())
+
+plt.show()

3217-classification-lr-example2.py

+from sklearn import datasets, neighbors, linear_model
+from sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay, f1_score
+import matplotlib.pyplot as plt
+
+X_digits, y_digits = datasets.load_digits(return_X_y=True)
+X_digits = X_digits / X_digits.max()
+
+n_samples = len(X_digits)
+
+ratio = 0.9
+print (n_samples)
+#train data
+X_train = X_digits[: int(ratio * n_samples)]
+y_train = y_digits[: int(ratio * n_samples)]
+print (X_train.shape)
+
+
+#test data
+
+X_test = X_digits[int(ratio * n_samples) :]
+y_test = y_digits[int(ratio * n_samples) :]
+print (X_test.shape)
+
+logistic = linear_model.LogisticRegression(max_iter=1000)
+
+print(
+    "LogisticRegression score: %f"
+    % logistic.fit(X_train, y_train).score(X_test, y_test))
+
+#Get results on actual test labels and predicted labels
+
+predictions = logistic.predict(X_test)
+
+#print (predictions)
+#print (y_test)
+#get f1 score
+
+print (f1_score(y_test, predictions, average='macro'))
+
+#get confusion matrix
+cm = confusion_matrix(y_test, predictions, labels=logistic.classes_)
+disp = ConfusionMatrixDisplay(confusion_matrix=cm,                           display_labels=logistic.classes_)
+disp.plot()
+plt.show()

3217-classification-lr-example3.py

+
+import numpy as np
+import matplotlib.pyplot as plt
+import pandas as pd
+
+from sklearn import datasets
+from sklearn.decomposition import PCA
+from sklearn.linear_model import LogisticRegression
+from sklearn.pipeline import Pipeline
+from sklearn.model_selection import GridSearchCV
+from sklearn.preprocessing import StandardScaler
+
+# Define a pipeline to search for the best combination of PCA truncation
+# and classifier regularization.
+pca = PCA()
+# Define a Standard Scaler to normalize inputs
+scaler = StandardScaler()
+
+# set the tolerance to a large value to make the example faster
+logistic = LogisticRegression(max_iter=10000, tol=0.1)
+pipe = Pipeline(steps=[("scaler", scaler), ("pca", pca), ("logistic", logistic)])
+
+X_digits, y_digits = datasets.load_digits(return_X_y=True)
+
+
+
+
+
+print (X_digits.shape)
+print (y_digits.shape)
+
+# Parameters of pipelines can be set using '__' separated parameter names:
+param_grid = {
+    "pca__n_components": [5, 15, 30, 45, 60],
+    "logistic__C": np.logspace(-1, 1, 1),
+}
+search = GridSearchCV(pipe, param_grid, n_jobs=2,cv=5)
+search.fit(X_digits, y_digits)
+print("Best parameter (CV score=%0.3f):" % search.best_score_)
+print(search.best_params_)
+
+# Plot the PCA spectrum
+pca.fit(X_digits)
+
+fig, (ax0, ax1) = plt.subplots(nrows=2, sharex=True, figsize=(6, 6))
+ax0.plot(
+    np.arange(1, pca.n_components_ + 1), pca.explained_variance_ratio_, "+", linewidth=2
+)
+ax0.set_ylabel("PCA explained variance ratio")
+
+ax0.axvline(
+    search.best_estimator_.named_steps["pca"].n_components,
+    linestyle=":",
+    label="n_components chosen",
+)
+ax0.legend(prop=dict(size=12))
+
+# For each number of components, find the best classifier results
+results = pd.DataFrame(search.cv_results_)
+print (results)
+components_col = "param_pca__n_components"
+best_clfs = results.groupby(components_col).apply(
+    lambda g: g.nlargest(1, "mean_test_score")
+)
+
+best_clfs.plot(
+    x=components_col, y="mean_test_score", yerr="std_test_score", legend=False, ax=ax1
+)
+ax1.set_ylabel("Classification accuracy (val)")
+ax1.set_xlabel("n_components")
+
+plt.xlim(-1, 70)
+
+plt.tight_layout()
+plt.show()

3217-classification-lr-example4.py

+
+import matplotlib.pyplot as plt
+import numpy as np
+from sklearn import datasets, linear_model
+from sklearn.metrics import mean_squared_error, r2_score
+
+# Load the diabetes dataset
+diabetes_X, diabetes_y = datasets.load_diabetes(return_X_y=True)
+
+print (diabetes_X.shape)
+# Use only one feature
+feature_to_use = 2
+diabetes_X = diabetes_X[:, np.newaxis, feature_to_use]
+print (diabetes_X.shape)
+
+test_samples = 20
+
+# Split the data into training/testing sets
+diabetes_X_train = diabetes_X[:-test_samples]
+diabetes_X_test = diabetes_X[-test_samples:]
+
+# Split the targets into training/testing sets
+diabetes_y_train = diabetes_y[:-test_samples]
+diabetes_y_test = diabetes_y[-test_samples:]
+
+
+
+
+# Create linear regression object
+regr = linear_model.LinearRegression()
+
+
+# Train the model using the training sets
+regr.fit(diabetes_X_train, diabetes_y_train)
+
+# Make prediction using the testing set
+diabetes_y_pred = regr.predict(diabetes_X_test)
+
+print (diabetes_y_train.shape)
+
+print (diabetes_y_test.shape)
+
+# The coefficients
+print("Coefficients: \n", regr.coef_)
+# The mean squared error
+print("Mean squared error: %.2f" % mean_squared_error(diabetes_y_test, diabetes_y_pred))
+# The coefficient of determination: 1 is perfect prediction
+print("Coefficient of determination: %.2f" % r2_score(diabetes_y_test, diabetes_y_pred))
+
+# Plot outputs
+plt.scatter(diabetes_X_test, diabetes_y_test, color="black") #grond truth actual test labels
+plt.scatter(diabetes_X_test, diabetes_y_pred, color="red")  #predicted   test labels
+
+plt.plot(diabetes_X_test, diabetes_y_pred, color="blue", linewidth=3)#predicted   test labels
+
+plt.xticks(())
+plt.yticks(())
+
+plt.show()

3217-classification-lr-example5.py

+#Import scikit-learn dataset library
+from sklearn import datasets
+from sklearn.model_selection import train_test_split
+from sklearn import svm, metrics
+
+
+
+#Load dataset
+cancer = datasets.load_breast_cancer()
+
+# print the names of the  features
+print("Features: ", cancer.feature_names)
+
+# print the label type of cancer('malignant' 'benign')
+print("Labels: ", cancer.target_names)
+
+# print data(feature)shape
+print (cancer.data.shape)
+
+
+# Split dataset into training set and test set
+X_train, X_test, y_train, y_test = train_test_split(cancer.data, cancer.target, test_size=0.2) # 70% training and 30% test
+
+
+#Create a svm Classifier
+clf = svm.SVC(kernel='linear') # Linear Kernel
+
+#Train the model using the training sets
+clf.fit(X_train, y_train)
+
+#Predict the response for test dataset
+y_pred = clf.predict(X_test)
+
+print("Accuracy:",metrics.accuracy_score(y_test, y_pred))