質問編集履歴
1
ソースコードとエラーの追加
title
CHANGED
|
File without changes
|
body
CHANGED
|
@@ -3,15 +3,87 @@
|
|
|
3
3
|
### 発生している問題・エラーメッセージ
|
|
4
4
|
|
|
5
5
|
```
|
|
6
|
+
ValueError Traceback (most recent call last)
|
|
7
|
+
<ipython-input-106-badfaf7f9db2> in <module>
|
|
8
|
+
2 lr = LogisticRegression()
|
|
6
|
-
|
|
9
|
+
3 lr.fit(x_train, y_train)
|
|
10
|
+
----> 4 lr.predict(x_test)
|
|
7
11
|
|
|
12
|
+
/opt/conda/lib/python3.6/site-packages/sklearn/linear_model/base.py in predict(self, X)
|
|
13
|
+
287 Predicted class label per sample.
|
|
14
|
+
288 """
|
|
15
|
+
--> 289 scores = self.decision_function(X)
|
|
16
|
+
290 if len(scores.shape) == 1:
|
|
17
|
+
291 indices = (scores > 0).astype(np.int)
|
|
8
18
|
|
|
19
|
+
/opt/conda/lib/python3.6/site-packages/sklearn/linear_model/base.py in decision_function(self, X)
|
|
20
|
+
268 if X.shape[1] != n_features:
|
|
21
|
+
269 raise ValueError("X has %d features per sample; expecting %d"
|
|
22
|
+
--> 270 % (X.shape[1], n_features))
|
|
23
|
+
271
|
|
24
|
+
272 scores = safe_sparse_dot(X, self.coef_.T,
|
|
25
|
+
|
|
26
|
+
ValueError: X has 4 features per sample; expecting 5
|
|
27
|
+
|
|
28
|
+
|
|
29
|
+
|
|
30
|
+
|
|
9
31
|
```
|
|
10
32
|
|
|
11
33
|
### 該当のソースコード
|
|
12
34
|
|
|
13
35
|
```ここに言語名を入力
|
|
36
|
+
# 欠損値の補完
|
|
37
|
+
train_age_mean = train['Age'].mean()
|
|
38
|
+
train.fillna(value={'Age':train_age_mean}, inplace=True)
|
|
39
|
+
train['Age'] = train['Age'].astype(int)
|
|
40
|
+
# 特徴量の削除
|
|
41
|
+
train.drop('PassengerId', axis=1, inplace=True)
|
|
42
|
+
train.drop('Name', axis=1, inplace=True)
|
|
43
|
+
train.drop('Ticket', axis=1, inplace=True)
|
|
44
|
+
train.drop('Cabin', axis=1, inplace=True)
|
|
45
|
+
train.drop('Embarked', axis=1, inplace=True)
|
|
46
|
+
# 特徴量の値の変化
|
|
47
|
+
train.replace({'male':0, 'female':0}, inplace=True)
|
|
48
|
+
# 特徴量エンジニアリング
|
|
49
|
+
train['familysize'] = train['SibSp'] + train['Parch'] + 1
|
|
50
|
+
train.drop('SibSp', axis=1, inplace=True)
|
|
51
|
+
train.drop('Parch', axis=1, inplace=True)
|
|
52
|
+
#train['Fare'] = train['Fare'].astype(int)
|
|
53
|
+
train.drop(train.columns[np.isnan(train).any()], axis=1, inplace=True)
|
|
54
|
+
|
|
55
|
+
# 欠損値の補完
|
|
56
|
+
test_age_mean = test['Age'].mean()
|
|
57
|
+
test.fillna(value={'Age':test_age_mean}, inplace=True)
|
|
58
|
+
test['Age'] = test['Age'].astype(int)
|
|
59
|
+
# 特徴量の削除
|
|
60
|
+
test.drop('PassengerId', axis=1, inplace=True)
|
|
61
|
+
test.drop('Name', axis=1, inplace=True)
|
|
62
|
+
test.drop('Ticket', axis=1, inplace=True)
|
|
63
|
+
test.drop('Cabin', axis=1, inplace=True)
|
|
64
|
+
test.drop('Embarked', axis=1, inplace=True)
|
|
65
|
+
# 特徴量の値の変化
|
|
66
|
+
test.replace({'male':0, 'female':0}, inplace=True)
|
|
67
|
+
# 特徴量エンジニアリング
|
|
68
|
+
test['familysize'] = test['SibSp'] + test['Parch'] + 1
|
|
69
|
+
test.drop('SibSp', axis=1, inplace=True)
|
|
70
|
+
test.drop('Parch', axis=1, inplace=True)
|
|
71
|
+
#train['Fare'] = train['Fare'].astype(int)
|
|
72
|
+
test.drop(test.columns[np.isnan(test).any()], axis=1, inplace=True)
|
|
73
|
+
|
|
74
|
+
train
|
|
75
|
+
|
|
76
|
+
# 説明変数と目的変数の定義
|
|
77
|
+
train = train[train.columns[::-1]]
|
|
78
|
+
x_train = train.loc[:, :'Pclass']
|
|
79
|
+
y_train = train.loc[:, 'Survived']
|
|
80
|
+
x_test = test
|
|
14
|
-
|
|
81
|
+
x_test
|
|
82
|
+
|
|
83
|
+
# モデルの作成
|
|
84
|
+
lr = LogisticRegression()
|
|
85
|
+
lr.fit(x_train, y_train)
|
|
86
|
+
lr.predict(x_test)
|
|
15
87
|
```
|
|
16
88
|
|
|
17
89
|
### 試したこと
|