#48 Classification

import os
import numpy as np
import matplotlib.pyplot as plt
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn import linear_model
from sklearn import metrics
from sklearn import tree
from sklearn import neighbors
from sklearn import svm
from sklearn import ensemble
from sklearn import cluster
import seaborn as sns
os.chdir(r'D:\projects\wordpress\ex48')
os.getcwd()
iris = datasets.load_iris()
print(type(iris))
print(iris.target_names)
print(iris.feature_names)
print(iris.data.shape)
print(iris.target.shape)
X_train, X_test, y_train, y_test = train_test_split(iris.data, iris.target, train_size=0.7)
classifier = linear_model.LogisticRegression()
print(classifier.fit(X_train, y_train))

y_test_pred = classifier.predict(X_test)
print(metrics.classification_report(y_test, y_test_pred))

print(np.bincount(y_test))
print(metrics.confusion_matrix(y_test, y_test_pred))

classifier = tree.DecisionTreeClassifier()
classifier.fit(X_train, y_train)
y_test_pred = classifier.predict(X_test)
print(metrics.confusion_matrix(y_test, y_test_pred))

classifier = neighbors.KNeighborsClassifier()
classifier.fit(X_train, y_train)
y_test_pred = classifier.predict(X_test)
print(metrics.confusion_matrix(y_test, y_test_pred))

classifier = svm.SVC()
classifier.fit(X_train, y_train)
y_test_pred = classifier.predict(X_test)
print(metrics.confusion_matrix(y_test, y_test_pred))

classifier = ensemble.RandomForestClassifier()
classifier.fit(X_train, y_train)
y_test_pred = classifier.predict(X_test)
print(metrics.confusion_matrix(y_test, y_test_pred))

train_size_vec = np.linspace(0.1, 0.9, 30)
classifiers = [tree.DecisionTreeClassifier,
               neighbors.KNeighborsClassifier,
               svm.SVC,
               ensemble.RandomForestClassifier
              ]
cm_diags = np.zeros((3, len(train_size_vec), len(classifiers)), dtype=float)
for n, train_size in enumerate(train_size_vec):
    X_train, X_test, y_train, y_test = \
        train_test_split(iris.data, iris.target, train_size=train_size)

[crayon-67674d732bb9e019976293/]

fig, axes = plt.subplots(4, 1, figsize=(6,18))

for m, Classifier in enumerate(classifiers):
    axes[m].plot(train_size_vec, cm_diags[2, :, m], label=iris.target_names[2])
    axes[m].plot(train_size_vec, cm_diags[1, :, m], label=iris.target_names[1])
    axes[m].plot(train_size_vec, cm_diags[0, :, m], label=iris.target_names[0])
    axes[m].set_title(type(Classifier()).<strong>name</strong>)
    axes[m].set_ylim(0, 1.1)
    axes[m].set_xlim(0.1, 0.9)
    axes[m].set_ylabel(&quot;classification accuracy&quot;)
    axes[m].set_xlabel(&quot;training size ratio&quot;)
    axes[m].legend(loc=4)

fig.tight_layout()
plt.savefig(&quot;example48.png&quot;, dpi=100)
plt.show()
plt.close()