我试图在以CSV格式存储的数据集上实现逻辑回归，然而，尽管实现这一点完全是网上的一个例子，显然我的数据还没有转换成一种格式，它可以在数字上工作。
我通常只使用c ++/java，所以所有这些python语法和处理这些数据集的函数对我来说相当混乱。
任何帮助都将不胜感激。

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib inline
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import classification_report

def calc_age(cols):
    Age = cols[0]
    Pclass = cols[1]
    
    if pd.isnull(Age):

        if Pclass == 1:
            return 37

        elif Pclass == 2:
            return 29

        else:
            return 24

    else:
        return Age

def driverMain():
    train = pd.read_csv('/Users/krishanbansal/Downloads/LogisticRegression-master/titanic_train.csv')
    test = pd.read_csv('/Users/krishanbansal/Downloads/LogisticRegression-master/titanic_test.csv')
    
    
    sns.heatmap(test.isnull(),yticklabels=False,cbar=False,cmap='viridis')
    
    train['Age'] = train[['Age','Pclass']].apply(calc_age,axis=1)
    test['Age'] = test[['Age','Pclass']].apply(calc_age,axis=1)
  
    sex = pd.get_dummies(train['Sex'],drop_first=True)
    embark = pd.get_dummies(train['Embarked'],drop_first=True)
    train.drop(['Sex','Embarked','Name','Ticket'],axis=1,inplace=True)
    train = pd.concat([train,sex,embark],axis=1)
    train.head()
    
    train.drop(['male','Q','S'],axis=1,inplace=True)
    
    sns.heatmap(train.isnull(),yticklabels=False,cbar=False,cmap='viridis')

    
    X_train, X_test, y_train, y_test = train_test_split(train.drop('Survived',axis=1),train['Survived'], test_size=0.20,random_state=101)
    
    logmodel = LogisticRegression()
    logmodel.fit(X_train,y_train)
    predictions = logmodel.predict(X_test)
    
    print(classification_report(y_test,predictions))
    print("Accuracy:",metrics.accuracy_score(y_test, predictions))
    
if __name__ == '__main__':
    driverMain()