[已解决]我的报错要怎么修改

嘴角向上

1. 报错

复制代码

0.35633487519024176 4
Traceback (most recent call last):
  File "C:\Users\zmj佳佳佳\Desktop\特征选择.py", line 41, in <module>
    plt.plot(range(1,201),superpa)
  File "C:\Users\zmj佳佳佳\AppData\Local\Programs\Python\Python38\lib\site-packages\matplotlib\pyplot.py", line 2761, in plot
    return gca().plot(
  File "C:\Users\zmj佳佳佳\AppData\Local\Programs\Python\Python38\lib\site-packages\matplotlib\axes\_axes.py", line 1646, in plot
    lines = [*self._get_lines(*args, data=data, **kwargs)]
  File "C:\Users\zmj佳佳佳\AppData\Local\Programs\Python\Python38\lib\site-packages\matplotlib\axes\_base.py", line 216, in __call__
    yield from self._plot_args(this, kwargs)
  File "C:\Users\zmj佳佳佳\AppData\Local\Programs\Python\Python38\lib\site-packages\matplotlib\axes\_base.py", line 342, in _plot_args
    raise ValueError(f"x and y must have same first dimension, but "
ValueError: x and y must have same first dimension, but have shapes (200,) and (5,)

1. import pandas as pd #导入数据集
   
2. url=r"C:\Users\zmj佳佳佳\Desktop\第六步离散化测试.csv"
   
3. df = pd.read_csv(url, header = None,low_memory=False)#将数据集分为训练集和测试集
   
4. df.columns=["grade","dti","delinq_2yrs","earliest_cr_line","fico_range_low","inq_last_6mths",
   
5.             "mths_since_last_delinq","pub_rec","revol_bal","revol_util","mths_since_last_major_derog",
   
6.             "tot_cur_bal","open_acc_6m","open_il_12m","open_il_24m","mths_since_rcnt_il","open_rv_12m",
   
7.             "open_rv_24m","max_bal_bc","all_util","inq_last_12m","acc_open_past_24mths","avg_cur_bal",
   
8.             "bc_open_to_buy","mo_sin_old_il_acct","mo_sin_old_rev_tl_op","mo_sin_rcnt_rev_tl_op","mo_sin_rcnt_tl",
   
9.            "mort_acc","mths_since_recent_bc_dlq","mths_since_recent_inq","mths_since_recent_revol_delinq",
   
10.             "num_accts_ever_120_pd","num_actv_bc_tl","num_actv_rev_tl","num_bc_sats","num_bc_tl",
    
11.             "num_rev_accts","num_rev_tl_bal_gt_0","num_tl_90g_dpd_24m","num_tl_op_past_12m","pct_tl_nvr_dlq",
    
12.             "pub_rec_bankruptcies"]
    
13. #将数据集分为训练集和测试集
    
14. from sklearn.model_selection import train_test_split
    
15. from sklearn.model_selection import GridSearchCV
    
16. from sklearn.ensemble import RandomForestClassifier
    
17. x, y = df.iloc[:, 1:].values, df.iloc[:, 0].values
    
18. x_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.3, random_state = 0)
    
19. feat_labels = df.columns[1:]
    
20. forest = RandomForestClassifier(min_samples_split=5,min_samples_leaf=3)
    
21. forest.fit(x_train, y_train)
    
22. #param={"n_estimators":[10,20],"max_depth":[5,8]}
    
23. #网格搜索与交叉验证
    
24. #gc=GridSearchCV(forest,param_grid=param,cv=3)
    
25. #gc.fit(x_train,y_train)
    
26. #print("准确率：",gc.score(x_test,y_test))
    
27. #print("查看选择的参数模型：",gc.best_params_)
    
28. 
    
29. 
    
30. #n_estimators的学习曲线
    
31. 
    
32. from sklearn.model_selection import cross_val_score
    
33. import matplotlib.pyplot as plt
    
34. superpa = []
    
35. for i in range(5):
    
36.     forest = RandomForestClassifier(n_estimators=i+1,n_jobs=-1)
    
37.     rfc_s = cross_val_score(forest,x,y,cv=2).mean()
    
38.     superpa.append(rfc_s)
    
39. print(max(superpa),superpa.index(max(superpa)))
    
40. plt.figure(figsize=[20,5])
    
41. plt.plot(range(1,201),superpa)
    
42. plt.show()
    
43. 
    
44. 
    
45. #特征重要性评估
    
46. import numpy as np
    
47. importances = forest.feature_importances_
    
48. indices = np.argsort(importances)[::-1]
    
49. for f in range(x_train.shape[1]):
    
50.     print("%2d) %-*s %f" % (f + 1, 30, feat_labels[indices[f]], importances[indices[f]]))
    

复制代码

最佳答案

月排行榜 / 总排行榜

BngThea

2020-4-9 20:26:05

你的superpa是一个含5个元素的列表，而x轴是1-200含两百个值，两者不匹配，画不了图

跳转到最佳答案楼层

BngThea

你的superpa是一个含5个元素的列表，而x轴是1-200含两百个值，两者不匹配，画不了图

嘴角向上

BngThea 发表于 2020-4-9 20:26
你的superpa是一个含5个元素的列表，而x轴是1-200含两百个值，两者不匹配，画不了图

嗯嗯，可以了，谢谢