理解熊猫的“类别”尺度

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score

# 假设我们有一个包含熊猫数据的DataFrame
data = {
    'Sex': ['Male', 'Female', 'Male', 'Female'],
    'Age': ['Adult', 'Cub', 'Adult', 'Cub'],
    'Location': ['Forest', 'Mountain', 'Forest', 'Mountain']
}
df = pd.DataFrame(data)

# 使用LabelEncoder将类别数据转换为数值
label_encoders = {}
for column in df.columns:
    le = LabelEncoder()
    df[column] = le.fit_transform(df[column])
    label_encoders[column] = le

# 分割数据集
X = df.drop('Location', axis=1)
y = df['Location']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=42)

# 训练模型
model = RandomForestClassifier()
model.fit(X_train, y_train)

# 预测和评估
y_pred = model.predict(X_test)
print(f'Accuracy: {accuracy_score(y_test, y_pred)}')