如何将HTML逗号分隔的字符串输入转换为NumPy数组并用于机器学习预测

<div>
    <form action="output">
        <table>
            <tr>
                <td align="right">特征值</td>
                <td align="left"><input type="text" name="n1"></td>
            </tr>
        </table>
        <input type="submit" value="提交">
    </form>
    <p>结果: {{ predictResult }}</p>
</div>

import numpy as np
# ... 其他代码 ...

def output(request):
    # ... 模型加载和训练代码 ...

    input_string = request.GET['n1']
    v1 = np.array((input_string)) # 错误地直接转换字符串

    # ... 预测代码 ...
    pred = model.predict([v1]) # 这里会报错
    # ...

ValueError at /prediction/output
Expected 2D array, got 1D array instead:
array=['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'].
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

input_string = request.GET['n1'] # 假设获取到的字符串是 "17.99,10.38,..."

# 1. 分割字符串并转换为浮点数列表
float_list = [float(num_str) for num_str in input_string.split(",")]

# 2. 将浮点数列表转换为 NumPy 数组
v1 = np.array(float_list)

# 此时 v1 的形状可能是 (n_features,)，是一个1D数组
# 例如：array([17.99, 10.38, ...])

# 承接上一步骤的 v1
# 假设 v1 的形状是 (n_features,)

v1_reshaped = v1.reshape(1, -1)

# 现在 v1_reshaped 的形状是 (1, n_features)，例如 (1, 30)
# 例如：array([[17.99, 10.38, ...]])

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 # 假设使用Django

def output(request):
    # 1. 数据加载与模型训练 (通常在应用启动时加载或缓存)
    # 为简化示例，这里直接加载和训练
    dff = pd.read_csv(r'C:\Users\Downloads\data.csv') # 请替换为实际路径
    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)
    model = LogisticRegression(max_iter=1000) # 增加max_iter以避免收敛警告
    model.fit(x_train, y_train)

    # 2. 获取前端输入并处理
    input_string = request.GET['n1']

    # 2.1 解析字符串并转换为浮点数数组
    # 使用列表推导式和 split() 方法
    try:
        v1_parsed = np.array([float(num) for num in input_string.split(",")])
    except ValueError:
        # 处理非数字输入的错误
        return render(request, 'prediction.html', {"predictResult": "输入数据格式错误，请确保只包含逗号分隔的数字。"})

    # 2.2 重塑数组以匹配模型输入要求 (1, n_features)
    # 确保输入特征的数量与模型训练时一致
    if v1_parsed.shape[0] != x_train.shape[1]:
        return render(request, 'prediction.html', {"predictResult": f"输入特征数量不匹配。期望 {x_train.shape[1]} 个，实际 {v1_parsed.shape[0]} 个。"})

    v1_final = v1_parsed.reshape(1, -1) # 重塑为 (1, n_features)

    # 3. 进行预测
    pred = model.predict(v1_final)

    # 4. 处理预测结果并返回
    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})