你会描述你的数据吗？

# -*- coding: utf-8 -*-
"""
描述你的数据
@author: Luqing Wang
"""
import matplotlib.pyplot as plt
import seaborn as sns

import pandas as pd

from sklearn import datasets
from sklearn.ensemble import RandomForestClassifier


if __name__ == "__main__":
    br = '\n'
    iris = datasets.load_iris()

    # 1 数据集概况分析
    X = iris.data
    y = iris.target
    print('特征集 shape:', X.shape)
    print('目标 shape:', y.shape, br)
    print('特征集 dtypes:', X.dtype)
    print('目标 dtypes:', y.dtype)
    features = iris.feature_names
    targets = iris.target_names
    print('特征集元数据:')
    print(features, br)
    print('目标元数据:')
    print(targets, br)

    # 2 数据观察
    print('iris数据集前10条数据：')
    print(X[0:10, :])

    # 3 数据摘要分析
    # 描述性统计分析
    print('特征集描述统计分析:')
    print(pd.DataFrame(X, columns=['sepal_length', 'sepal_width', 'petal_length', 'petal_width']).describe().T)
    print('目标的分布：')
    print(pd.Series(y).value_counts())

    # 4 变量重要性分析
    # 利用随机森林算法来评估变量的重要性
    rnd_clf = RandomForestClassifier(random_state=0, n_estimators=100)
    rnd_clf.fit(X, y)
    rnd_name = rnd_clf.__class__.__name__
    feature_importances = rnd_clf.feature_importances_
    importance = sorted(zip(feature_importances, features), reverse=True)
    print('most important features' + ' (' + rnd_name + '):')
    [print (row) for i, row in enumerate(importance)]

    # 5 数据可视化分析
    iris_data = pd.DataFrame(X, columns=['sepal_length', 'sepal_width', 'petal_length', 'petal_width'])
    iris_data['species'] = y
    sns.pairplot(iris_data, vars=['sepal_length', 'sepal_width', 'petal_length', 'petal_width'], hue='species')
    plt.show()