Python打卡第7天

@浙大疏锦行

作业：

01 02 03 04 05 06 07 08 09 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70

importpandas as pd heartdf=pd.read_csv('Python打卡训练营\Python打卡训练营\python60-days-challenge-master\heart.csv') # 先看数据长什么样 print(heartdf.head()) print(heartdf.shape) print(heartdf.columns) print(heartdf.dtypes) print(heartdf.info()) # 体检看看有无异常值 print(heartdf.describe(percentiles=[.25, .5, .75, .9])) # 检查缺失值（有则进行清洗、填补） print(heartdf.isnull().sum()) missing_ratio=heartdf.isnull().sum()/len(heartdf)*100 print(missing_ratio) # 对于非分类的特征画图查看是否有异常值 importmatplotlib.pyplot as plt importseaborn as sns importmath categorical_features=[ 'sex', 'cp', 'fbs', 'restecg', 'exang', 'slope', 'ca', 'thal' ] label='target' continuous_features=[ colforcolinheartdf.columns ifcolnotincategorical_featuresandcol !=label ] n_cols=3 n_rows=math.ceil(len(continuous_features)/n_cols) fig, axes=plt.subplots( n_rows, n_cols, figsize=(15,4*n_rows) ) # 转成一维，方便遍历 axes=axes.flatten() fori, colinenumerate(continuous_features): sns.boxplot( x=heartdf[col], ax=axes[i] ) axes[i].set_title(f'Boxplot of {col}') # 如果最后一行没有填满，把多余子图删掉 forjinrange(len(continuous_features),len(axes)): fig.delaxes(axes[j]) plt.tight_layout() plt.show() # 后续还要做标准化，防止数据泄露，划分数据集，时间序列还需要做滑动窗口