探索数据科学家的日常：揭秘职业背后的故事

import pandas as pd
import numpy as np

# 假设我们有一个包含缺失值和异常值的数据集
data = pd.DataFrame({
    'age': [25, 30, np.nan, 28, 120],
    'salary': [5000, 7000, 6000, np.nan, 9000]
})

# 处理缺失值
data['age'].fillna(data['age'].median(), inplace=True)
data['salary'].fillna(data['salary'].mean(), inplace=True)

# 处理异常值（假设年龄超过100为异常）
data['age'] = np.where(data['age'] > 100, data['age'].median(), data['age'])

print(data)

import matplotlib.pyplot as plt

# 可视化薪资分布
plt.hist(data['salary'], bins=5, edgecolor='k')
plt.xlabel('Salary')
plt.ylabel('Frequency')
plt.title('Salary Distribution')
plt.show()

from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error

# 假设我们要预测薪资
X = data[['age']]
y = data['salary']

# 划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# 构建线性回归模型
model = LinearRegression()
model.fit(X_train, y_train)

# 预测与评估
y_pred = model.predict(X_test)
print(f"Mean Squared Error: {mean_squared_error(y_test, y_pred)}")