基于《机器学习-Python实践》学习笔记 3第一个机器学习项目

第三章 第一个机器学习项目

共进行了五步

1. 导入数据
2. 概述数据

# 导入类库
from pandas import read_csv
from pandas.plotting import scatter_matrix
from matplotlib import pyplot
from sklearn.model_selection import train_test_split
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
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.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.neighbors import KNeighborsClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.svm import SVC

# 导入数据
filename = 'iris.data.csv'
names = ['separ-length', 'separ-width', 'petal-length', 'petal-width', 'class']
dataset = read_csv(filename, names=names)#读取文件，将names列表中的四个值作为读取后每一列的表头

#显示数据维度
print('数据维度: 行 %s，列 %s' % dataset.shape)#矩阵.shape返回（行，列）
# 查看数据的前10行
print(dataset.head(10))

# 统计描述数据信息
print(dataset.describe())#描述数据：行数、中位数、最大值、最小值、均值、四分位值

# 分类分布情况
print(dataset.groupby('class').size())

输出结果：

3. 数据可视化

用三种图对比数据

# 箱线图
dataset.plot(kind='box', subplots=True, layout=(2,2), sharex=False, sharey=False)
pyplot.show()

# 直方图
dataset.hist()
pyplot.show()

# 散点矩阵图
scatter_matrix(dataset)
pyplot.show()

5. 评估算法
   将数据分离为8:2的训练集和测试集

6. 实时预测

# 导入类库
from pandas import read_csv
from pandas.plotting import scatter_matrix
from matplotlib import pyplot
from sklearn.model_selection import train_test_split
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
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.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.neighbors import KNeighborsClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.svm import SVC

# 导入数据
filename = 'iris.data.csv'
names = ['separ-length', 'separ-width', 'petal-length', 'petal-width', 'class']
dataset = read_csv(filename, names=names)#读取文件，将names列表中的四个值作为读取后每一列的表头

# 分离数据集
array = dataset.values
X = array[:, 0:4]
Y = array[:, 4]
validation_size = 0.2
seed = 7
X_train, X_validation, Y_train, Y_validation = \
    train_test_split(X, Y, test_size=validation_size, random_state=seed)

# 算法审查
models = {}
models['LR'] = LogisticRegression()
models['LDA'] = LinearDiscriminantAnalysis()
models['KNN'] = KNeighborsClassifier()
models['CART'] = DecisionTreeClassifier()
models['NB'] = GaussianNB()
models['SVM'] = SVC()
# 评估算法
results = []
for key in models:
    kfold = KFold(n_splits=10, random_state=seed)
    cv_results = cross_val_score(models[key], X_train, Y_train, cv=kfold, scoring='accuracy')
    results.append(cv_results)
    print('%s: %f (%f)' %(key, cv_results.mean(), cv_results.std()))

# 箱线图比较算法
fig = pyplot.figure()
fig.suptitle('Algorithm Comparison')
ax = fig.add_subplot(111)
pyplot.boxplot(results)
ax.set_xticklabels(models.keys())
pyplot.show()

#使用评估数据集评估算法
svm = SVC()
svm.fit(X=X_train, y=Y_train)
predictions = svm.predict(X_validation)
print(accuracy_score(Y_validation, predictions))
print(confusion_matrix(Y_validation, predictions))
print(classification_report(Y_validation, predictions))