我有一个关于糖尿病患者的数据集，有很多示例。
每个示例都用特定的类（二进制，0或1）进行分类（标记）
我在尝试预测Y ^时遇到了问题
但我有问题

import numpy as np 
import pandas as pd
from sklearn.model_selection import train_test_split 

def load_cvs(filename):
    data = []
    labels = []

    with open(filename,  'r') as f:
        for line in f:
            items = line.split(",")
            data.append([float(items[0]),float(items[1]),float(items[2]),float(items[3]),float(items[4]),float(items[5])])
            labels.append(int(items[6]))
    return np.array(data), np.array(labels)

X,y = load_cvs('diabetes.csv')
df = pd.read_csv("diabetes.csv")
#Glucose;BloodPressure;SkinThickness;Insulin;BMI;Age

X_train, X_test, y_train, y_test = train_test_split(X, y,test_size=0.2, random_state=33)

def sigmoid(z):
     return 1 / (1 + np.exp(-z))

def predict(X,w):
    z = np.dot(X,w)
    return sigmoid(z)

def cost(y , y_pred):
    return -np.mean(y * np.log(y_pred) + (1 - y) * np.log(1 - y_pred))

def train(X, y, epochs = 1000, lr =0.02):
    X = np.c_[np.ones((X.shape[0], 1)), X]

    w = np.random.randn(X.shape[1])

    for epoch in range(epochs):
        y_pred = predict(X,w)
        error = y_pred - y

    gradient = np.dot(X.T, error) / y.size

    w -= lr * gradient

    if epoch % 100 == 0:
        c = cost(y,y_pred)
        print(f'Epoch{epoch}: cost = {c}')
        return w

w = train(X_train,y_train,epochs=1000, lr=0.02)
X_test=X_test

y_pred = predict(np.c_[np.ones((X_test.shape[0], 1)),  X_test], w)

我收到此错误消息：TypeError: unsupported operand type(s) for *: 'float' and 'NoneType'
我更改了代码，但仍有问题

import numpy as np
from random import seed
from random import randrange
from sklearn.model_selection import train_test_split
from csv import reader
import pandas as pd
from sklearn.linear_model import LogisticRegression

from sklearn import preprocessing

from sklearn.metrics import accuracy_score, classification_report, confusion_matrix

from matplotlib import pyplot as plt

import seaborn as sns

def load_cvs(filename):
    data = []
    labels = []

    with open(filename,  'r') as f:
        for line in f:
            items = line.split(",")
            data.append([float(items[0]),float(items[1]),float(items[2]),float(items[3]),float(items[4]),float(items[5])])
            labels.append(int(items[6]))
    return np.array(data), np.array(labels)
seed(1)

col_names = ['Glucose','BloodPressure','SkinThickness','Insulin','BMI','Age','Outcome']
df = pd.read_csv('diabetes.csv', header=None, names=col_names)
nandf = df.fillna(value=0)
#nandf = df[df.isna().any(axis=1)]
#nandf.head()

feature_cols = ['Glucose','BloodPressure','SkinThickness','Insulin','BMI','Age']
X = nandf[feature_cols] # Features
y = nandf.Outcome # Target variable



X_train, X_test, y_train, y_test = train_test_split(X, y,test_size=0.2, random_state=16)





def sigmoid(z):
     return 1 / (1 + np.exp(-z))

def predict(X,w):
    z = np.dot(X,w)
    return sigmoid(z)

def cost(y , y_pred):
    return -np.mean(y * np.log(y_pred) + (1 - y) * np.log(1 - y_pred))

def train(X, y, epochs = 1000, lr =0.02):
    X = np.c_[np.ones((X.shape[0], 1)), X]

    w = np.random.randn(X.shape[1])

    for epoch in range(epochs):
        y_pred = predict(X,w)
        error = y_pred - y

    gradient = np.dot(X.T, error) / y.size

    w -= lr * gradient

    if epoch % 100 == 0:
        c = cost(y,y_pred)
        print(f'Epoch{epoch}: cost = {c}')
        return w


w = train(X_train,y_train,epochs=1000, lr=0.02)

y_pred = predict(np.c_[np.ones((X_test.shape[0], 1)),  X_test], w) # this line[enter image description here][1]

#print(f'prediction: {y_pred}')

enter image description here
enter image description here