0
# -*- coding: utf-8 -*-
"""
Created on Wed Apr 26 21:28:31 2017
@author: Chirantan
"""
import pandas
from pandas.tools.plotting import scatter_matrix
import matplotlib.pyplot as plt
from sklearn import model_selection
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix
from sklearn.metrics import accuracy_score
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.naive_bayes import GaussianNB
from sklearn.svm import SVC
# Load dataset
url = "https://archive.ics.uci.edu/ml/machine-learning-databases/yeast/yeast.data"
names = ['Sequence Name','mcg', 'gvh', 'alm', 'mit', 'erl','pox','vac','nuc']
dataset = pandas.read_csv(url, names=names, delim_whitespace=True)
# shape
print(dataset.shape)
# head
print(dataset.head(20))
# descriptions
print(dataset.describe())
# class distribution
#print(dataset.groupby('').size())
# box and whisker plots
dataset.plot(kind='box', subplots=True, layout=(10,10), sharex=False, sharey=False)
plt.show()
# histograms
dataset.hist()
plt.show()
# scatter plot matrix
scatter_matrix(dataset)
plt.show()
# histograms
dataset.hist()
plt.show()
# scatter plot matrix
scatter_matrix(dataset)
plt.show()
# Split-out validation dataset
array = dataset.values
X = array[:,0:9]
Y = array[:,9]#HERE IS THE ERROR
validation_size = 0.20
seed = 7
X_train, X_validation, Y_train, Y_validation = model_selection.train_test_split(X, Y, test_size=validation_size, random_state=seed)
# Test options and evaluation metric
seed = 7
scoring = 'accuracy'
# Spot Check Algorithms
models = []
models.append(('LR', LogisticRegression()))
models.append(('LDA', LinearDiscriminantAnalysis()))
models.append(('KNN', KNeighborsClassifier()))
models.append(('CART', DecisionTreeClassifier()))
models.append(('NB', GaussianNB()))
models.append(('SVM', SVC()))
# evaluate each model in turn
results = []
names = []
for name, model in models:
kfold = model_selection.KFold(n_splits=10, random_state=seed)
cv_results = model_selection.cross_val_score(model, X_train, Y_train, cv=kfold, scoring=scoring)
results.append(cv_results)
names.append(name)
msg = "%s: %f (%f)" % (name, cv_results.mean(), cv_results.std())
print(msg)
# Compare Algorithms
fig = plt.figure()
fig.suptitle('Algorithm Comparison')
ax = fig.add_subplot(111)
plt.boxplot(results)
ax.set_xticklabels(names)
plt.show()
# Make predictions on validation dataset
#knn = KNeighborsClassifier()
svm = SVC()
svm.fit(X_train, Y_train)
predictions = svm.predict(X_validation)
#knn.fit(X_train, Y_train)
#predictions = knn.predict(X_validation)
print(accuracy_score(Y_validation, predictions))
print(confusion_matrix(Y_validation, predictions))
print(classification_report(Y_validation, predictions))
我试图用不同的分类从UCI repository.Everything多类酵母数据集工作正常与上面的代码与虹膜数据集有以下变化只是我在Python中使用酵母数据出了界限错误问题。为什么？
# Split-out validation dataset
array = dataset.values
X = array[:,0:4]
Y = array[:,4]
validation_size = 0.20
但它无法正常工作与当我做这个
# Split-out validation dataset
array = dataset.values
X = array[:,0:9]
Y = array[:,9]
validation_size = 0.20
这里酵母数据集是错误messaage
File "<ipython-input-40-707d4eef8576>", line 55, in <module>
Y = array[:,9]
IndexError: index 9 is out of bounds for axis 1 with size 9
我不明白这个.array存储数据集的值，现在array [：，9]会给我最后一列。我错了吗？请帮忙。
没有索引9。 – bhansa