我如何通过预测承认或拒绝定标器来修复问题

如何解决我如何通过预测承认或拒绝定标器来修复问题

我正在尝试使用 spyder python 3.8 根据大学指标预测录取的可能性...

df = pd.read_csv (r'C:\Users\neuro\AdmissionPredictFile.csv')
col_names=df.columns.tolist()
df.drop(['Serial No.'],axis=1,inplace=True)
var=df.columns.values.tolist()
y=df['Chance of Admit']
X=[i for i in var if i not in ['Chance of Admit']]
X=df[X]
from sklearn.model_selection import train_test_split
X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.25,random_state=0)
from sklearn.preprocessing import MinMaxScaler
xs=MinMaxScaler()
X_train[X_train.columns] = xs.fit_transform(X_train[X_train.columns])
X_test[X_test.columns] = xs.transform(X_test[X_test.columns])
import numpy as np
cy_train=[1 if chance > 0.82 else 0 for chance in y_train]
cy_train=np.array(cy_train)
cy_test=[1 if chance > 0.82 else 0 for chance in y_test]
cy_test=np.array(cy_test)
from sklearn.linear_model import LogisticRegression
lr = LogisticRegression()
lr.fit(X_train,cy_train)
from sklearn.metrics import accuracy_score
print('Train Logistic regression accuracy: {:.3f}'.format(accuracy_score(cy_train,lr.predict(X_train))))
print('Test Logistic regression accuracy: {:.3f}'.format(accuracy_score(cy_test,lr.predict(X_test))))
print('--------------------------------------')
from sklearn.metrics import classification_report
print(classification_report(cy_test,lr.predict(X_test)))
cls = lr.predict(X_test)
from sklearn.ensemble import RandomForestClassifier
rf = RandomForestClassifier()
rf.fit(X_train,cy_train)
print('Train Random Forest Accuracy: {:.3f}'.format(accuracy_score(cy_train,rf.predict(X_train))))
print('Test Random Forest Accuracy: {:.3f}'.format(accuracy_score(cy_test,rf.predict(X_test))))
print('--------------------------------------')
print(classification_report(cy_test,rf.predict(X_test)))
from sklearn.svm import SVC
svc = SVC()
svc.fit(X_train,cy_train)
print('Train Support vector machine accuracy: {:.3f}'.format(accuracy_score(cy_train,svc.predict(X_train))))
print('Test Support vector machine accuracy: {:.3f}'.format(accuracy_score(cy_test,svc.predict(X_test))))
print('--------------------------------------')
print(classification_report(cy_test,svc.predict(X_test)))
feature_importance=pd.Series(rf.feature_importances_,index=X_train.columns).sort_values(ascending=False)
print(feature_importance)
import seaborn as sns
sns.heatmap(df.corr(),annot=True,linewidths=0.05,fmt= '.2f',cmap="Pastel2")

model = rf.fit
rf.fit(X_train,cy_train)
new_data = [(0,2,1.0,1,1.3,0) ]
new_array = np.asarray(new_data)
labels=["We're sorry,but it's a rejection.","--Congratulations,it's an accpetance!--"]
predictions = rf.predict(X_test)
prediction=rf.predict(new_array)
no_of_test_cases,cols = new_array.shape
for i in range(no_of_test_cases):
     print("Based on the following submitted results TOEFL score = {},University rating = {},SOP = {},LOR = {},Research = {},CGPA = {} you are likely to receive the following response from your desired institution ----- {}".format(new_data[i][0],new_data[i][1],new_data[i][2],new_data[i][3],new_data[i][4],new_data[i] [5],labels[int(prediction[i])]))

但是，当我尝试测试预测器并为申请人提供较低的拒绝消息结果时，他们仍然收到“通过”消息。我觉得我的 minmax 缩放器出了问题，因为我实际上没有收到错误消息...

model = rf.fit
rf.fit(X_train,cy_train)
new_data = [(33,10,3,3.0,7.0,0)]
new_array = np.asarray(new_data)
labels=["We're sorry,cols = new_array.shape
for i in range(no_of_test_cases):
     print("Based on the following submitted results GRE score = {},TOEFL score = {},new_data[i] [6],labels[int(prediction[i])]))
 

根据以下提交的结果，GRE 分数 = 33，托福分数 = 10，大学评分 = 3，SOP = 3.0，LOR = 2，研究 = 7.0，CGPA = 0，您可能会收到以下回复机构 ----- --恭喜，这是一个acceptance！--