ADD file via upload

import numpy.py

@@ -0,0 +1,184 @@
+import numpy as np
+import pandas as pd
+
+from sklearn import datasets
+from sklearn.neighbors import KNeighborsClassifier#估计器
+from sklearn.ensemble import RandomForestClassifier#估计器
+#管道
+from sklearn.model_selection import train_test_split#数据训练集、测试集划分
+from sklearn.preprocessing import StandardScaler#预处理器、转化器
+from sklearn.pipeline import make_pipeline
+from sklearn.pipeline import Pipeline#管道
+from sklearn.metrics import accuracy_score#准确性计算
+#交叉验证
+from sklearn.datasets import make_regression
+from sklearn.model_selection import cross_validate
+from sklearn.linear_model import LinearRegression
+#自动参数搜索
+from sklearn.datasets import fetch_california_housing
+from sklearn.model_selection import RandomizedSearchCV
+from scipy.stats import randint
+from sklearn.ensemble import RandomForestRegressor
+
+import matplotlib.pyplot as plt #python可视化库
+import seaborn as sns
+from sklearn.model_selection  import cross_val_score
+from matplotlib.colors import ListedColormap
+from sklearn import neighbors
+import operator
+
+def run_KNN(X,X_train,y_train,K):  #需要预测的数据集,训练集,训练集,K个最近
+    dataSize = X_train.shape[0]
+    y_predict = []
+    for x in X:
+        diff = np.tile(x,(dataSize,1)) - X_train # 把X扩大然后矩阵相减
+        squaredDist = np.sum(diff**2,axis=1) # axis = 1计算每一行的和
+        distance = squaredDist ** 0.5
+ 
+        # 对距离递增排序获取最前面K个样本的种类并统计各种类出现次数
+        nearIds = distance.argsort() # 按值排序，得到对应下标数组
+        classesCount = {}
+        for i in range(K):
+            y = y_train[nearIds[i]] # 得到对应的种类
+            classesCount[y] = classesCount.get(y,0)+1 # 0为设置默认值
+        # print(classesCount)
+        # 对字典按值进行递减排序
+        sortClassesCount = sorted(classesCount.items(),key=operator.itemgetter(1),reverse=True)
+                                                        # 获取对象第二个元素           逆序
+        y_predict.append(sortClassesCount[0][0])  # 预测种类为出现次数最多的那一类
+    return y_predict
+
+sns.set_style("whitegrid")
+
+
+filename = 'iris\iris.data'
+data= pd.read_csv(filename,usecols=[0,1,2,3],header=None,names=["sepal length","sepal width","petal length","petal width"])
+target = pd.read_csv(filename,usecols=[4],header=None,names=["type"])
+test=pd.read_csv(filename,header=None,names=["sepal length","sepal width","petal length","petal width","type"])
+
+pipe=make_pipeline(
+    StandardScaler(),#预处理器/转化器（特征缩放）
+   KNeighborsClassifier() #估计器
+)
+
+x = data
+y = target
+#划分鸢尾花数据集
+x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.3)
+#求取k值
+k_range = range(1, 31)
+k_error = []
+index=0
+min=1
+#循环，取k=1到k=31，查看误差效果
+for k in k_range:
+    pipe.fit(x_train,np.ravel(y_train))
+    Pipeline(steps=[('standardscaler', StandardScaler()),('kneighborsclassfier', KNeighborsClassifier(n_neighbors=k))])
+    #10折交叉验证
+    scores = cross_val_score(KNeighborsClassifier(n_neighbors=k), x_train, y_train, cv=10, scoring='accuracy')
+    k_error.append(1 - scores.mean())
+    if k==1:
+        index=k;
+    elif k>1 and k_error[k-1]<min:
+        index=k;
+        min=k_error[k-1]
+
+#画图，x轴为k值，y值为误差值
+plt.plot(k_range, k_error)
+plt.xlabel('Value of K for KNN')
+plt.ylabel('Error')
+plt.show()
+print("最小误差为：",min)
+print("最小k值为：",index)
+
+
+
+# print(type(iris_x[0]))
+# print(iris_x[:2])
+# print(iris_y[:2])
+
+# print(x_test)
+# print(y_test)
+pipe.fit(x_test,np.ravel(y_test))#格式转化
+knn=Pipeline(steps=[('standardscaler', StandardScaler()),('kneighborsclassfier', KNeighborsClassifier(n_neighbors=index))])
+ans=pipe.predict(x_test)
+#ans1=run_KNN(test,x_train,y_train,index)
+print(type(y_test))
+y_test=y_test.values
+for i in range(0,len(ans)):
+    print(" ",y_test[i][0],ans[i])
+    
+
+
+print("scikit-learn knn模型预估准确度为：",accuracy_score(pipe.predict(x_test),y_test))#准确度
+#print("knn模型预估准确度为：",accuracy_score(ans1,y_test))#准确度
+# kn=KNeighborsClassifier()
+# ra=RandomForestClassifier(random_state=0)
+# # print(ra.predict(x_test))
+# # print(y_test)
+# StandardScaler().fit(iris_x).transform(iris_x) 
+# ra.fit(x_train,y_train)
+# print(ra.predict(x_test))
+# print(y_test)
+
+#线性回归交叉验证
+X, y = make_regression(n_samples=1000, random_state=0)
+lr = LinearRegression()
+result = cross_validate(lr, X, y)  #
+print(result['test_score'])  # r_squared score is high because dataset is easy
+print("1.查看数据集直方图")
+print("2.查看数据集波形图")
+print("3.查看数据集特征关系图")
+print("4.查看数据集箱形图")
+print("0.退出")
+while(1):
+    a=input()
+    if a=='1':
+        test.hist(bins=15)#绘制测试集各类花瓣直方图
+        plt.show()
+    elif a=='2':
+        test.plot.area(stacked=False)#波形图
+        plt.show()
+    elif a=='3':
+        sns.pairplot(test,hue="type",height=3)
+        plt.show()
+    elif a=='4':
+        fig,axes=plt.subplots(2,2,figsize=(10,8))
+        sns.boxplot(y=test["sepal length"],x=test["type"],ax=axes[0,0])
+        sns.boxplot(y=test["sepal width"],x=test["type"],ax=axes[0,1])
+        sns.boxplot(y=test["petal length"],x=test["type"],ax=axes[1,0])
+        sns.boxplot(y=test["petal width"],x=test["type"],ax=axes[1,1])
+        plt.show()
+    elif a=='0':
+        break
+
+ 
+#特征两两关系图
+# data.plot(kind="kde")#KDE图
+# sns.heatmap(data.corr(),annot=True,cmap="YlGnBu")
+# 
+# print(data.describe())
+
+
+
+
+# #自动参数搜索
+# x,y=fetch_california_housing(return_X_y=True);
+# x_train,x_test,y_train,y_test=train_test_split(iris_x,iris_y,test_size=0.3)
+# param_distributions = {'n_estimators': randint(1, 5),
+#                     'max_depth': randint(5, 10)}
+# search = RandomizedSearchCV(estimator=RandomForestRegressor(random_state=0),
+#                             n_iter=5,
+#                             param_distributions=param_distributions,
+#                             random_state=0)
+# search.fit(x_train, y_train)
+# RandomizedSearchCV(estimator=RandomForestRegressor(random_state=0), n_iter=5,
+#                    param_distributions={'max_depth': ...,
+#                                         'n_estimators': ...},
+#                    random_state=0)
+# search.best_params_
+# {'max_depth': 9, 'n_estimators': 4}
+# print(search.score(x_test, y_test))
+# 使用KNN预测数据类别
+
+