分类器可视化

这本笔记本的目的是让你可视化各种分类器的决策边界。

本笔记本中使用的数据基于存储在mushrooms.csv中的UCI蘑菇数据集。

为了更好地确定决策边界，我们将对数据执行主成分分析（PCA）以将维度降至2维。 降维将在本课程后面的模块中介绍。

玩弄不同的模型和参数，看看它们如何影响分类器的决策边界和准确性！

%matplotlib notebook

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.decomposition import PCA
from sklearn.model_selection import train_test_split

df = pd.read_csv('mushrooms.csv')
df2 = pd.get_dummies(df)

df3 = df2.sample(frac=0.08)

X = df3.iloc[:,2:]
y = df3.iloc[:,1]


pca = PCA(n_components=2).fit_transform(X)

X_train, X_test, y_train, y_test = train_test_split(pca, y, random_state=0)


plt.figure(dpi=120)
plt.scatter(pca[y.values==0,0], pca[y.values==0,1], alpha=0.5, label='Edible', s=2)
plt.scatter(pca[y.values==1,0], pca[y.values==1,1], alpha=0.5, label='Poisonous', s=2)
plt.legend()
plt.title('Mushroom Data Set
First Two Principal Components')
plt.xlabel('PC1')
plt.ylabel('PC2')
plt.gca().set_aspect('equal')

def plot_mushroom_boundary(X, y, fitted_model):

    plt.figure(figsize=(9.8,5), dpi=100)
    
    for i, plot_type in enumerate(['Decision Boundary', 'Decision Probabilities']):
        plt.subplot(1,2,i+1)

        mesh_step_size = 0.01  # step size in the mesh
        x_min, x_max = X[:, 0].min() - .1, X[:, 0].max() + .1
        y_min, y_max = X[:, 1].min() - .1, X[:, 1].max() + .1
        xx, yy = np.meshgrid(np.arange(x_min, x_max, mesh_step_size), np.arange(y_min, y_max, mesh_step_size))
        if i == 0:
            Z = fitted_model.predict(np.c_[xx.ravel(), yy.ravel()])
        else:
            try:
                Z = fitted_model.predict_proba(np.c_[xx.ravel(), yy.ravel()])[:,1]
            except:
                plt.text(0.4, 0.5, 'Probabilities Unavailable', horizontalalignment='center',
                     verticalalignment='center', transform = plt.gca().transAxes, fontsize=12)
                plt.axis('off')
                break
        Z = Z.reshape(xx.shape)
        plt.scatter(X[y.values==0,0], X[y.values==0,1], alpha=0.4, label='Edible', s=5)
        plt.scatter(X[y.values==1,0], X[y.values==1,1], alpha=0.4, label='Posionous', s=5)
        plt.imshow(Z, interpolation='nearest', cmap='RdYlBu_r', alpha=0.15, 
                   extent=(x_min, x_max, y_min, y_max), origin='lower')
        plt.title(plot_type + '
' + 
                  str(fitted_model).split('(')[0]+ ' Test Accuracy: ' + str(np.round(fitted_model.score(X, y), 5)))
        plt.gca().set_aspect('equal');
        
    plt.tight_layout()
    plt.subplots_adjust(top=0.9, bottom=0.08, wspace=0.02)

from sklearn.linear_model import LogisticRegression

model = LogisticRegression()
model.fit(X_train,y_train)

plot_mushroom_boundary(X_test, y_test, model)

from sklearn.neighbors import KNeighborsClassifier

model = KNeighborsClassifier(n_neighbors=20)
model.fit(X_train,y_train)

plot_mushroom_boundary(X_test, y_test, model)

from sklearn.tree import DecisionTreeClassifier

model = DecisionTreeClassifier(max_depth=3)
model.fit(X_train,y_train)

plot_mushroom_boundary(X_test, y_test, model)

from sklearn.tree import DecisionTreeClassifier

model = DecisionTreeClassifier()
model.fit(X_train,y_train)

plot_mushroom_boundary(X_test, y_test, model)

from sklearn.ensemble import RandomForestClassifier

model = RandomForestClassifier()
model.fit(X_train,y_train)

plot_mushroom_boundary(X_test, y_test, model)

from sklearn.svm import SVC

model = SVC(kernel='linear')
model.fit(X_train,y_train)

plot_mushroom_boundary(X_test, y_test, model)

from sklearn.svm import SVC

model = SVC(kernel='rbf', C=1)
model.fit(X_train,y_train)

plot_mushroom_boundary(X_test, y_test, model)

from sklearn.svm import SVC

model = SVC(kernel='rbf', C=10)
model.fit(X_train,y_train)

plot_mushroom_boundary(X_test, y_test, model)

from sklearn.naive_bayes import GaussianNB

model = GaussianNB()
model.fit(X_train,y_train)

plot_mushroom_boundary(X_test, y_test, model)

from sklearn.neural_network import MLPClassifier

model = MLPClassifier()
model.fit(X_train,y_train)

plot_mushroom_boundary(X_test, y_test, model)