Python机器学习报错求助：ValueError无法将字符串转为浮点

错误原因 #

你用于训练的特征集X包含字符串类型的name列（例如"Bright Green"），而Scikit-learn的LogisticRegression模型仅支持数值型输入，无法自动将字符串转换为浮点数，因此触发该错误。

解决方案 #

以下提供三种可行的解决方式，按实用性排序：

方案3：基于关键词提取特征（最优）

观察数据可发现，所有半透明颜色的名称均包含"Trans"关键词，直接提取该特征即可完成分类，准确率接近100%：

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score

data = pd.read_csv('colors_without_rgb.csv')

# 从name列提取是否包含"Trans"的特征，转为整数类型
data['has_trans'] = data['name'].str.contains('Trans', case=False).astype(int)
X = data[["has_trans"]]
# 将目标变量的't'/'f'转为1/0，适配模型要求
y = data['is_trans'].map({'t': 1, 'f': 0})

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

model = LogisticRegression()
model.fit(X_train, y_train)

predictions = model.predict(X_test)
accuracy = accuracy_score(y_test, predictions)
print(f"Accuracy: {accuracy:.2f}")

方案1：使用唯一标识id作为特征

每个颜色对应唯一的id，直接用id作为输入特征即可规避字符串问题：

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score

data = pd.read_csv('colors_without_rgb.csv')

# 仅保留id列作为特征
X = data[["id"]]
y = data['is_trans'].map({'t': 1, 'f': 0})

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

model = LogisticRegression()
model.fit(X_train, y_train)

predictions = model.predict(X_test)
accuracy = accuracy_score(y_test, predictions)
print(f"Accuracy: {accuracy:.2f}")

方案2：对name列进行独热编码

若需直接使用颜色名称作为特征，可通过独热编码将字符串转换为模型可识别的数值型特征：

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score
from sklearn.preprocessing import OneHotEncoder
from sklearn.compose import ColumnTransformer
from sklearn.pipeline import Pipeline

data = pd.read_csv('colors_without_rgb.csv')

X = data[["name"]]
y = data['is_trans'].map({'t': 1, 'f': 0})

# 创建预处理管道，对name列执行独热编码
preprocessor = ColumnTransformer(
    transformers=[
        ('category_encoder', OneHotEncoder(handle_unknown='ignore'), ['name'])
    ])

# 构建包含预处理和模型的完整管道
model = Pipeline(steps=[
    ('preprocessor', preprocessor),
    ('classifier', LogisticRegression())
])

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

model.fit(X_train, y_train)

predictions = model.predict(X_test)
accuracy = accuracy_score(y_test, predictions)
print(f"Accuracy: {accuracy:.2f}")

内容的提问来源于stack exchange，提问作者EdwardTheTrain