从HTML表单接收逗号分隔值并转化为NumPy数组以供模型预测的教程

import numpy as np

input_str = "17.99,10.38,122.8"
v1_incorrect = np.array(input_str)
print(v1_incorrect)
# 输出: array('17.99,10.38,122.8', dtype='<U17')
print(v1_incorrect.shape)
# 输出: ()  # 这是一个0维数组，其元素是一个字符串

v1_incorrect_alt = np.array([input_str])
print(v1_incorrect_alt)
# 输出: ['17.99,10.38,122.8']
print(v1_incorrect_alt.shape)
# 输出: (1,) # 这是一个1维数组，包含一个字符串元素

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

# 假设这是从 request.GET['n1'] 获取到的字符串
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"

# 1. 分割字符串并转换为浮点数列表
numerical_list = [float(num.strip()) for num in input_string.split(',')]

# 2. 创建一维NumPy数组
v1_1d = np.array(numerical_list)

print("一维NumPy数组:", v1_1d)
print("数组形状:", v1_1d.shape)
# 输出示例:
# 一维NumPy数组: [ 17.99  10.38 122.8  ...   0.4601  0.1189]
# 数组形状: (30,)

# 假设 v1_1d 是上一步创建的一维NumPy数组
# 将一维数组重塑为二维数组 (1 行, N 列)，其中 N 是特征数量
v1_2d = v1_1d.reshape(1, -1)

print("重塑后的二维NumPy数组:", v1_2d)
print("重塑后数组形状:", v1_2d.shape)
# 输出示例:
# 重塑后的二维NumPy数组: [[ 17.99  10.38 122.8  ...   0.4601  0.1189]]
# 重塑后数组形状: (1, 30)

import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from django.shortcuts import render # 假设在Django框架中

def output(request):
    # --- 数据加载和模型训练部分 (与原代码保持一致，但建议添加随机种子和max_iter) ---
    try:
        dff = pd.read_csv(r'C:\Users\Downloads\data.csv')
    except FileNotFoundError:
        return render(request, 'prediction.html', {"predictResult": "错误：数据集文件未找到。"})

    y = dff['diagnosis'].values
    x = dff.drop('diagnosis', axis=1).values

    # 建议添加 random_state 以确保数据分割的可复现性
    # 建议增加 max_iter 避免 LogisticRegression 的收敛警告
    x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.40, random_state=42)

    model = LogisticRegression(max_iter=1000) 
    model.fit(x_train, y_train)
    # --- 数据加载和模型训练部分结束 ---

    pred1 = ""
    # 获取用户输入，使用 .get() 方法并提供默认值以避免 KeyError
    input_string = request.GET.get('n1', '') 

    if not input_string:
        pred1 = "请输入有效的特征数据。"
    else:
        try:
            # 步骤一：解析字符串并转换为浮点数数组
            # 使用 .strip() 清除可能存在的空白字符
            numerical_values = [float(num.strip()) for num in input_string.split(',')]
            v1_1d = np.array(numerical_values)

            # 验证输入特征数量是否与模型训练时的特征数量一致
            expected_features = x_train.shape[1]
            if v1_1d.shape[0] != expected_features:
                pred1 = f"输入特征数量不匹配。模型期望 {expected_features} 个特征，但实际输入了 {v1_1d.shape[0]} 个。"
            else:
                # 步骤二：调整数组形状以匹配模型输入
                v1_2d = v1_1d.reshape(1, -1) # 重塑为单样本的2D数组

                # 进行预测
                pred = model.predict(v1_2d)
                pred1 = "positive" if pred[0] == 1 else "negative"

        except ValueError:
            # 捕获因非数字字符导致的转换错误
            pred1 = "输入数据格式错误，请检查是否为逗号分隔的数字。"
        except Exception as e:
            # 捕获其他未知错误
            pred1 = f"处理请求时发生未知错误: {e}"

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

<!-- prediction.html -->
<div>
    <form action="output" method="GET"> <!-- 确保method与后端request.GET匹配 -->
        <table>
            <tr>
                <td align="right">特征值 (逗号分隔):</td>
                <!-- 提示用户输入格式，并设置合适的name属性 -->
                <td align="left"><input type="text" name="n1" placeholder="例如: 17.99,10.38,122.8,..."></td>
            </tr>
        </table>
        <input type="submit" value="提交预测">
    </form>

    <h3>预测结果: {{ predictResult }}</h3>
</div>