Python数据分析代写

# Advanced Data Analysis with Python
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import mean_squared_error, r2_score

# Data loading and exploration
df = pd.read_csv('dataset.csv')
print(df.info())
print(df.describe())

# Data preprocessing
df_clean = df.dropna()
df_clean['log_feature'] = np.log1p(df_clean['feature'])

# Beautiful visualization
plt.figure(figsize=(12, 8))
sns.scatterplot(data=df_clean, x='feature1', y='target', 
                hue='category', alpha=0.7)
plt.title('Feature Relationship Analysis')
plt.tight_layout()
plt.show()

# Machine learning pipeline
X = df_clean.drop('target', axis=1)
y = df_clean['target']

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

# Model training and evaluation
model = RandomForestRegressor(n_estimators=100, random_state=42)
model.fit(X_train, y_train)

y_pred = model.predict(X_test)
mse = mean_squared_error(y_test, y_pred)
r2 = r2_score(y_test, y_pred)

print(f'MSE: {mse:.4f}')
print(f'R²: {r2:.4f}')