【Python自然语言处理】使用SVM、随机森林法、梯度法等多种方法对病人罹患癌症预测实战（超详细 附源码）

#导入库
import matplotlib
import matplotlib.pyplot as plt 
import seaborn as sn 
from sklearn.svm import SVC
import numpy as np
import pandas as pds 
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.ensemble import AdaBoostClassifier
from sklearn.metrics import accuracy_score
from sklearn.metrics import confusion_matrix
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.neighbors import KNeighborsClassifier
import xgboost as xgb
from matplotlib import font_manager
from sklearn.neighbors import LocalOutlierFactor
from sklearn.model_selection import train_test_split
#from sklearn.neighbors import NeighborhoodComponentsAnalysis
fontP = font_manager.FontProperties()
fontP.set_family('SimHei')
fontP.set_size(14)
# In[2]:
# 加载数据
dr = pds.read_csv('./data/data.csv')
# In[3]:
dr.head(5)
# In[4]:
dr.info()
# In[5]:
#dr.drop(['id','Unnamed: 32','fractal_dimension_worst','symmetry_worst','concave points_worst','concavity_worst','compactness_worst','smoothness_worst','area_worst','perimeter_worst','texture_worst','radius_worst','fractal_dimension_se','symmetry_se','concave points_se','concavity_se','compactness_se','smoothness_se','area_se','perimeter_se','texture_se','radius_se','radius_se'], axis = 1 , inplace=True)
dr.drop(['id','Unnamed: 32','texture_mean','smoothness_mean','compactness_mean','concavity_mean','concave points_mean','symmetry_mean','fractal_dimension_mean','fractal_dimension_worst','symmetry_worst','concave points_worst','concavity_worst','compactness_worst','smoothness_worst','area_worst','perimeter_worst','texture_worst','radius_worst','fractal_dimension_se','symmetry_se','concave points_se','concavity_se','compactness_se','smoothness_se','area_se','perimeter_se','texture_se','radius_se','radius_se'], axis = 1 , inplace=True)
dr.info()
# In[6]:
dr.diagnosis.replace({"B":0,"M":1},inplace=True)
# **目标数据进行归类:**
# 
# * 恶性肿瘤 - 1
# * 良性肿瘤 - 0
# In[7]:
correlation = dr.corr()
plt.figure(figsize=(7,7))
sn.set(font_scale=1.2)
sn.set(font='SimHei')
sn.heatmap(correlation, cmap='Purples',annot = True,annot_kws={"size": 12}, linewidths=0, linecolor='white', cbar=True, cbar_kws=None, cbar_ax=None, square=False)
# In[8]:
sn.heatmap(correlation, cmap='Purples', xticklabels=['诊断结果', '半径均值', '周长均值', '面积均值'],yticklabels=['诊断结果','半径均值','周长均值', '面积均值'],annot = True,annot_kws={"size": 10}, linewidths=0, linecolor='white', cbar=True, cbar_kws=None, cbar_ax=None, square=False)
# In[9]:
correlation[abs(correlation['diagnosis']) > 0.68].index
# In[10]:
dr.drop('diagnosis', axis=1).corrwith(dr.diagnosis).plot(kind='bar', grid=True, figsize=(6, 6), title="Correlation",color="purple");
# **相关性** 
# * 选择相关性不小于68%作为阈值，分析特征值与罹患恶性肿瘤的关系.
# 
# In[11]:
correlation = dr.corr()
cancer_threshold = 0.68 
filter = np.abs(correlation["diagnosis"]) >= cancer_threshold
correlation.filter = correlation.columns[filter].tolist()
sn.set(font_scale=5.5)
sn.set(font='SimHei')
#sn.clustermap(dr[cf].corr(), figsize=(6, 6), xticklabels=['诊断结果', '面积均值','半径均值', '周长均值'],yticklabels=['周长均值', '半径均值', '面积均值', '诊断结果'],annot = True, annot_kws={"size": 12},cmap="Purples").fig.suptitle("罹患肿瘤相关性分析", fontproperties=fontP,x=0.6, y=1.0) 
res=sn.clustermap(dr.corr(), figsize=(6, 6),annot = True, annot_kws={"size": 16},cmap="Purples").fig.suptitle("罹患肿瘤相关性分析", fontproperties=fontP,x=0.6, y=1.0) 
# In[ ]:
# In[12]:
#组图
sn.set(font_scale=1.5)
sn.set_style(style='white')
sn.pairplot(dr[correlation.filter],dropna=True,grid_kws=None,  diag_kind = "kde", markers = ".", hue = "diagnosis", palette='Purples')
# **去除异常节点** 
# In[13]:
from sklearn.neighbors import LocalOutlierFactor
# 将数据划分为自变量和因变量
y=dr["diagnosis"]
x=dr.drop(["diagnosis"],axis=1)
# In[14]:
# -1代表异常节点
outlier= LocalOutlierFactor()
y.predict=outlier.fit_predict(x)
y.predict[0:10]
# In[15]:
x_factor= outlier.negative_outlier_factor_
pds.dataframe= pds.DataFrame()
pds.dataframe["score"]=x_factor
threshold= -2.5
data_filter= pds.dataframe["score"]< threshold
pds_filter_tolist= pds.dataframe[data_filter].index.tolist()
# In[17]:
x= x.drop(pds_filter_tolist)
y= y.drop(pds_filter_tolist).values
# In[18]:
x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2,random_state=42)
scaler = StandardScaler()
x_nsform(x_test)
# In[19]:
index = ['梯度法','逻辑回归法','近邻法','支持向量机法','决策树法','随机森林法']
model_list = [GradientBoostingClassifier(),LogisticRegression(), KNeighborsClassifier(n_neighbors = 4), SVC(kernel="rbf"), DecisionTreeClassifier(), RandomForestClassifier(n_estimators=600)]
model_dict = dict(zip(index,model_list))
model_dict
# In[20]:
pediction_outcome_list =[]
for i,j in model_dict.items():
    j.fit(x_train,y_train)
    x_prediction = j.predict(x_test)
    accuracy = accuracy_score(y_test, x_prediction)
    pediction_outcome_list.append(accuracy)
    print(i,"{:.4f}".format(accuracy))
# In[21]:
plt.figure(figsize = (10,4))
sn.barplot(x =index , y =pediction_outcome_list, palette="vlag",  ci=95,edgecolor='purple',n_boot=1000, dodge=False)
# In[22]:
gradient_boost = GradientBoostingClassifier(loss='deviance',  learning_rate=0.1)
result_list = []
accuracy = []
for j in range(1,28,1):
    x_train,x_test,y_train,y_test = train_test_split(x, y, test_size = 0.25, random_state = j)    
    gradient_boost_fit = gradient_boost.fit(x_train, y_train)
    fit_predict_x = gradient_boost_fit.predict(x_test)
    accuracy.append(accuracy_score(y_test, fit_predict_x))
    result_list.append(j)
# In[23]:
plt.figure(figsize=(10,8))
plt.xlabel("迭代次数",fontsize=14)
plt.
# In[ ]: