机器学习_01_算法最优

机器学习入门01

1. 准备工作：下载iris.data.csv文件（其实就是excel文件）
   下载链接
   如下图

#   01.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
    #   02.导入数据
    filename="iris.data.csv"
    names= ['separ-length','separ-width','petal-length','petal-width','class']
    dataset=read_csv(filename,names=names
                    )
    #  03.显示数据维度
    print('数据维度：行%s,列%s'% dataset.shape)

 #  04.查看数据前10行
    print(dataset.head(10))

  #  05.统计描述数据信息
    print(dataset.describe())

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

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

  #  08.直方图
    dataset.hist()
    pyplot.show()

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

#  10.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)
# 11.算法审查
models = {}
models['LR'] = LogisticRegression()
models['LDA'] = LinearDiscriminantAnalysis()
models['KNN'] = KNeighborsClassifier()
models['CART'] = DecisionTreeClassifier()
models['NB'] = GaussianNB()
models['SVM'] =SVC()

#  12.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()))

完整代码如下：”

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
#   02.导入数据
filename="iris.data.csv"
names= ['separ-length','separ-width','petal-length','petal-width','class']
dataset=read_csv(filename,names=names
                )
#  03.显示数据维度
print('数据维度：行%s,列%s'% dataset.shape)

#  04.查看数据前10行
print(dataset.head(10))

#  05.统计描述数据信息
print(dataset.describe())

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

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

#  08.直方图
dataset.hist()
pyplot.show()

scatter_matrix(dataset)
pyplot.show()

#  10.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)

# 11.算法审查
models = {}
models['LR'] = LogisticRegression()
models['LDA'] = LinearDiscriminantAnalysis()
models['KNN'] = KNeighborsClassifier()
models['CART'] = DecisionTreeClassifier()
models['NB'] = GaussianNB()
models['SVM'] =SVC()

#  12.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()))