drop_list1 = ['perimeter_mean','radius_mean','compactness_mean','concave points_mean','radius_se','perimeter_se','radius_worst','perimeter_worst','compactness_worst','concave points_worst','compactness_se','concave points_se','texture_worst','area_worst']
x_1 = x.drop(drop_list1,axis = 1 ) # do not modify x, we will use it later
x_1.head()

#correlation map
f,ax = plt.subplots(figsize=(14, 14))
sns.heatmap(x_1.corr(), annot=True, linewidths=.5, fmt= '.1f',ax=ax)

from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import f1_score,confusion_matrix
from sklearn.metrics import accuracy_score # split data train 70 % and test 30 %
x_train, x_test, y_train, y_test = train_test_split(x_1, y, test_size=0.3, random_state=42) #random forest classifier with n_estimators=10 (default)
clf_rf = RandomForestClassifier(random_state=43)
clr_rf = clf_rf.fit(x_train,y_train) ac = accuracy_score(y_test,clf_rf.predict(x_test))
print('Accuracy is: ',ac)
cm = confusion_matrix(y_test,clf_rf.predict(x_test))
sns.heatmap(cm,annot=True,fmt="d")

from sklearn.feature_selection import SelectKBest
from sklearn.feature_selection import chi2
# find best scored 5 features
select_feature = SelectKBest(chi2, k=5).fit(x_train, y_train)
print('Score list:', select_feature.scores_)
print('Feature list:', x_train.columns)

x_train_2 = select_feature.transform(x_train)
x_test_2 = select_feature.transform(x_test)
#random forest classifier with n_estimators=10 (default)
clf_rf_2 = RandomForestClassifier()
clr_rf_2 = clf_rf_2.fit(x_train_2,y_train)
ac_2 = accuracy_score(y_test,clf_rf_2.predict(x_test_2))
print('Accuracy is: ',ac_2)
cm_2 = confusion_matrix(y_test,clf_rf_2.predict(x_test_2))
sns.heatmap(cm_2,annot=True,fmt="d")

from sklearn.feature_selection import RFE
# Create the RFE object and rank each pixel
clf_rf_3 = RandomForestClassifier()
rfe = RFE(estimator=clf_rf_3, n_features_to_select=5, step=1)
rfe = rfe.fit(x_train, y_train)
print('Chosen best 5 feature by rfe:',x_train.columns[rfe.support_])

from sklearn.feature_selection import RFECV

# The "accuracy" scoring is proportional to the number of correct classifications
clf_rf_4 = RandomForestClassifier()
rfecv = RFECV(estimator=clf_rf_4, step=1, cv=5,scoring='accuracy') #5-fold cross-validation
rfecv = rfecv.fit(x_train, y_train) print('Optimal number of features :', rfecv.n_features_)
print('Best features :', x_train.columns[rfecv.support_])
# Plot number of features VS. cross-validation scores
import matplotlib.pyplot as plt
plt.figure()
plt.xlabel("Number of features selected")
plt.ylabel("Cross validation score of number of selected features")
plt.plot(range(1, len(rfecv.grid_scores_) + 1), rfecv.grid_scores_)
plt.show()

clf_rf_5 = RandomForestClassifier()
clr_rf_5 = clf_rf_5.fit(x_train,y_train)
importances = clr_rf_5.feature_importances_
std = np.std([tree.feature_importances_ for tree in clf_rf.estimators_],
axis=0)
indices = np.argsort(importances)[::-1] # Print the feature ranking
print("Feature ranking:") for f in range(x_train.shape[1]):
print("%d. feature %d (%f)" % (f + 1, indices[f], importances[indices[f]])) # Plot the feature importances of the forest plt.figure(1, figsize=(14, 13))
plt.title("Feature importances")
plt.bar(range(x_train.shape[1]), importances[indices],
color="g", yerr=std[indices], align="center")
plt.xticks(range(x_train.shape[1]), x_train.columns[indices],rotation=90)
plt.xlim([-1, x_train.shape[1]])
plt.show()

# split data train 70 % and test 30 %
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.3, random_state=42)
#normalization
x_train_N = (x_train-x_train.mean())/(x_train.max()-x_train.min())
x_test_N = (x_test-x_test.mean())/(x_test.max()-x_test.min()) from sklearn.decomposition import PCA
pca = PCA()
pca.fit(x_train_N) plt.figure(1, figsize=(14, 13))
plt.clf()
plt.axes([.2, .2, .7, .7])
plt.plot(pca.explained_variance_ratio_, linewidth=2)
plt.axis('tight')
plt.xlabel('n_components')
plt.ylabel('explained_variance_ratio_')

吴裕雄--天生自然 PYTHON数据分析:威斯康星乳腺癌(诊断)数据分析(续一)的更多相关文章

  1. 吴裕雄--天生自然 PYTHON数据分析:糖尿病视网膜病变数据分析(完整版)

    # This Python 3 environment comes with many helpful analytics libraries installed # It is defined by ...

  2. 吴裕雄--天生自然 PYTHON数据分析:所有美国股票和etf的历史日价格和成交量分析

    # This Python 3 environment comes with many helpful analytics libraries installed # It is defined by ...

  3. 吴裕雄--天生自然 python数据分析:健康指标聚集分析(健康分析)

    # This Python 3 environment comes with many helpful analytics libraries installed # It is defined by ...

  4. 吴裕雄--天生自然 python数据分析:葡萄酒分析

    # import pandas import pandas as pd # creating a DataFrame pd.DataFrame({'Yes': [50, 31], 'No': [101 ...

  5. 吴裕雄--天生自然 PYTHON数据分析:人类发展报告——HDI, GDI,健康,全球人口数据数据分析

    import pandas as pd # Data analysis import numpy as np #Data analysis import seaborn as sns # Data v ...

  6. 吴裕雄--天生自然 python数据分析:医疗费数据分析

    import numpy as np import pandas as pd import os import matplotlib.pyplot as pl import seaborn as sn ...

  7. 吴裕雄--天生自然 PYTHON语言数据分析:ESA的火星快车操作数据集分析

    import os import numpy as np import pandas as pd from datetime import datetime import matplotlib imp ...

  8. 吴裕雄--天生自然 python语言数据分析:开普勒系外行星搜索结果分析

    import pandas as pd pd.DataFrame({'Yes': [50, 21], 'No': [131, 2]}) pd.DataFrame({'Bob': ['I liked i ...

  9. 吴裕雄--天生自然 PYTHON数据分析:基于Keras的CNN分析太空深处寻找系外行星数据

    #We import libraries for linear algebra, graphs, and evaluation of results import numpy as np import ...

随机推荐

  1. LGOJ1264 K-联赛

    这题其实不难想到 Description link 题意太长了,概括不来,去题库里扫一眼吧(但是很好懂) Solution \[Begin\] 考虑一个事情:每一个队伍的输局是没有用的 贪心一下,让每 ...

  2. Spring事务管理 —— readOnly只读事务

    事务是什么?事务是一个原子操作,由一系列动作组成.事务的原子性确保动作要么全部完成,要么完全不起作用. 下面来看一个项目中遇到的问题: 有这么一个需求,我们要查询一些数据,但是在查询这个数据之前我们要 ...

  3. Java 实现 栈

    package Test; import java.util.*; public class Stack_test { public static void main(String[] args) { ...

  4. Centos7安装Xrdp远程桌面

    Xrdp是Microsoft远程桌面协议RDP的一个开源实现,它允许以图像方式控制远程系统. 测试环境 服务端: CentOS Linux release 7.7.1908 (Core) 客户端: W ...

  5. Python笔记_第一篇_面向过程_第一部分_5.Python数据类型之列表类型(list)

    Python中序列是最基本的数据结构.序列中的每个元素都分配一个数字(他的位置或者索引),第一个索引是0,第二个索引是1,依次类推.Python的列表数据类型类似于C语言中的数组,但是不同之处在于列表 ...

  6. goweb-web服务

    Web服务 Web服务可以让你在HTTP协议的基础上通过XML或者JSON来交换信息.如果你想知道上海的天气预报.中国石油的股价或者淘宝商家的一个商品信息,你可以编写一段简短的代码,通过抓取这些信息然 ...

  7. c语言中getchar的用法

    /************************************************************************* > File Name: getchar2. ...

  8. Windows Server 2008 R2 安全加固

    0x00 简介 安全加固是企业安全中及其重要的一环,其主要内容包括账号安全.认证授权.协议安全.审计安全四项,这篇博客简单整理一下Windows Server 2008 R2的安全加固方案. 0x01 ...

  9. bootstrap-table 实现父子表

    1.引入相关的css和js <link type="text/css" href="/components/bootstrap/3.3.7/css/bootstra ...

  10. 奇点云 x 阿里云 | 联合发布综合体数字化转型与数据创新解决方案

    2019年7月25日下午,在阿里云峰会上海站,奇点云入选阿里云首批联合解决方案合作伙伴,并联合发布了“综合体数字化转型与数据创新解决方案”,共同探索综合体的智能服务. 关于综合体的数字化转型,奇点云联 ...