sklearn分类器简单比较

你好

数据：leaf_data

---

import pandas as pd

import numpy as np

import matplotlib.pyplot as plt

from sklearn.preprocessing import LabelEncoder

from sklearn.preprocessing import StandardScaler

from sklearn.model_selection import StratifiedShuffleSplit

train_data = pd.read_csv("train.csv")

LABELS = train_data['species']

# 将train_data中的‘id’列弹出。

ID = train_data.pop('id')

# print train_data[0:1]

# 将train_data中的‘species’列弹出。

y = train_data.pop('species')

# 将species向量化。

y = LabelEncoder().fit(y).transform(y)

print y

# standardize the data by setting the mean to 0 and std to 1

standardize = True

X = StandardScaler().fit(train_data).transform(train_data) if standardize else train_data.values

print X[0:1]

from sklearn.decomposition import PCA, IncrementalPCA

n_components = 60

#ipca = IncrementalPCA(n_components=n_components, batch_size=20)

#X_ipca = ipca.fit_transform(X)

pca = PCA(n_components=n_components)

X_pca = pca.fit_transform(X)

'''

colors = ['navy', 'turquoise', 'darkorange', 'blue', 'purple', 'green',

'yellow','red','pink', 'palegoldenrod','navy', 'turquoise', 'darkorange', 'blue', 'purple', 'green',

'yellow','red','pink', 'palegoldenrod','navy', 'turquoise', 'darkorange', 'blue', 'purple', 'green',

'yellow','red','pink', 'palegoldenrod',]

for X_transformed, title in [(X_ipca, "Incremental PCA"), (X_pca, "PCA")]:

plt.figure(figsize=(8, 8))

for color, i, target_name in \

zip(colors, [0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24], LABELS):

plt.scatter(X_transformed[y == i, 0], X_transformed[y == i, 1],

color=color, lw=2, label=target_name)

if "Incremental" in title:

err = np.abs(np.abs(X_pca) - np.abs(X_ipca)).mean()

plt.title(title + " of iris dataset\nMean absolute unsigned error "

"%.6f" % err)

else:

plt.title(title + " of iris dataset")

#plt.legend(loc="best", shadow=False, scatterpoints=1)

plt.axis([-10, 10, -10, 10])

plt.show()'''

from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4, random_state=0)

from sklearn.ensemble import RandomForestClassifier

from subprocess import check_output

forest = RandomForestClassifier(n_estimators = 100)

forest = forest.fit(X_train, y_train)

output = forest.score(X_test, y_test)

print 'RandomForestClassifier:', output

from sklearn import tree

regressor = tree.DecisionTreeClassifier()

regressor = regressor.fit(X_train, y_train)

score = regressor.score(X_test, y_test)

print 'Decision Tree:', score

from sklearn import svm

Svm = svm.SVC()

Svm = Svm.fit(X_train, y_train)

Svm_score = Svm.score(X_test, y_test)

print 'svm:', Svm_score

from sklearn import neighbors

n_neighbors = 2

weights = 'uniform'

KNN = neighbors.KNeighborsClassifier(n_neighbors, weights=weights)

KNN = KNN.fit(X_train, y_train)

KNN_score = KNN.score(X_test, y_test)

print 'KNN:', KNN_score

from sklearn.ensemble import AdaBoostClassifier

Ada = AdaBoostClassifier(n_estimators=100)

Ada = Ada.fit(X_train, y_train)

Ada_score = Ada.score(X_test, y_test)

print 'AdaBoostClassifier:', Ada_score

from sklearn.neural_network import MLPClassifier

MLP = MLPClassifier(solver='lbfgs', alpha=1e-5, hidden_layer_sizes=(500, 300), random_state=1)

MLP = MLP.fit(X_train, y_train)

MLP_score = MLP.score(X_test, y_test)

print 'MLPClassifier:', MLP_score

from sklearn.naive_bayes import GaussianNB

gnb = GaussianNB()

gnb = gnb.fit(X_train, y_train)

gnb_score = gnb.score(X_test, y_test)

print 'GaussianNB:', gnb_score

---

未进行PCA降维结果：

PCA降维后结果：