从HTML表单获取逗号分隔值并转换为NumPy数组进行预测

# HTML input (e.g., from request.GET['n1'])
user_input_string = "17.99,10.38,122.8,1001,0.1184,0.2776,0.3001,0.1471,0.2419,0.07871,1.095,0.9053,8.589,153.4,0.006399,0.04904,0.05373,0.01587,0.03003,0.006193,25.38,17.33,184.6,2019,0.1622,0.6656,0.7119,0.2654,0.4601,0.1189"

# 错误的初步转换尝试
import numpy as np
v1 = np.array(user_input_string)
print(v1)
print(v1.shape)

['17.99,10.38,122.8,...']
(1,)

ValueError: Expected 2D array, got 1D array instead:
array=['17.99,10.38,122.8,...'].
Reshape your data either using array.reshape(-1, 1) if your data has a single feature or array.reshape(1, -1) if it contains a single sample.

import numpy as np

user_input_string = "17.99,10.38,122.8,1001,0.1184,0.2776,0.3001,0.1471,0.2419,0.07871,1.095,0.9053,8.589,153.4,0.006399,0.04904,0.05373,0.01587,0.03003,0.006193,25.38,17.33,184.6,2019,0.1622,0.6656,0.7119,0.2654,0.4601,0.1189"

# 将字符串按逗号分割，并将每个部分转换为浮点数
numerical_list = [float(num) for num in user_input_string.split(",")]

# 将浮点数列表转换为NumPy一维数组
v1_1d = np.array(numerical_list)

print(v1_1d)
print(v1_1d.shape)
print(v1_1d.dtype)

[ 17.99   10.38  122.8  ...   0.4601   0.1189]
(30,)
float64

# 承接上一步的 v1_1d
v1_final = v1_1d.reshape(1, -1)

print(v1_final)
print(v1_final.shape)

[[ 17.99   10.38  122.8  ...   0.4601   0.1189]]
(1, 30)

v1 = np.array([float(num) for num in request.GET['n1'].split(",")]).reshape(1, -1)

import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from django.shortcuts import render

def output(request):
    # 加载数据并训练模型（这部分通常在应用启动时完成，此处为演示简化）
    dff = pd.read_csv(r'C:\Users\Downloads\data.csv')
    y = dff['diagnosis'].values
    x = dff.drop('diagnosis', axis=1).values
    x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.40, random_state=42) # 添加random_state保证可复现性
    model = LogisticRegression(max_iter=1000) # 增加max_iter防止收敛警告
    model.fit(x_train, y_train)

    # 获取用户输入字符串
    user_input_string = request.GET.get('n1', '') # 使用.get()方法提供默认值，避免KeyError

    # 核心修改：处理用户输入，转换为正确的NumPy数组格式
    try:
        # 1. 分割字符串并转换为浮点数列表
        numerical_values = [float(num) for num in user_input_string.split(",")]
        # 2. 转换为NumPy一维数组，并重塑为(1, n_features)的二维数组
        v1 = np.array(numerical_values).reshape(1, -1)
    except ValueError:
        # 处理转换失败的情况，例如用户输入了非数字字符或格式不正确
        pred1 = "输入格式错误，请确保输入的是逗号分隔的数值。"
        return render(request, 'prediction.html', {"predictResult": pred1})
    except Exception as e:
        # 捕获其他可能的异常
        pred1 = f"处理输入时发生未知错误: {e}"
        return render(request, 'prediction.html', {"predictResult": pred1})

    # 使用处理后的v1进行预测
    pred = model.predict(v1)
    pred1 = ""
    if pred[0] == 1: # pred是一个数组，需要取第一个元素
        pred1 = "positive"
    else:
        pred1 = "negative"

    return render(request, 'prediction.html', {"predictResult": pred1})