回答編集履歴
3
追記
answer
CHANGED
|
@@ -14,15 +14,15 @@
|
|
|
14
14
|
# 標準偏差= 1.7716909687891083
|
|
15
15
|
```
|
|
16
16
|
|
|
17
|
-
|
|
17
|
+
どうしてもstatisticsでやりたい場合は、data_listを1次元に落とし込んでから使う手もあります。
|
|
18
18
|
```python3
|
|
19
19
|
import pandas as pd
|
|
20
20
|
import statistics
|
|
21
|
-
import numpy as np
|
|
22
21
|
|
|
23
22
|
df = pd.DataFrame([[1, 2], [1, 3], [4, 6]], columns=['A', 'B'])
|
|
24
23
|
data_list = df.values.tolist()
|
|
24
|
+
data_list = sum(data_list, []) # [1, 2, 1, 3, 4, 6]
|
|
25
|
-
hensa =
|
|
25
|
+
hensa = statistics.pstdev(data_list)
|
|
26
26
|
print("標準偏差=",hensa)
|
|
27
|
-
# 標準偏差= 1.
|
|
27
|
+
# 標準偏差= 1.7716909687891083
|
|
28
28
|
```
|
2
追記
answer
CHANGED
|
@@ -12,4 +12,17 @@
|
|
|
12
12
|
hensa = np.std(data_list)
|
|
13
13
|
print("標準偏差=",hensa)
|
|
14
14
|
# 標準偏差= 1.7716909687891083
|
|
15
|
+
```
|
|
16
|
+
|
|
17
|
+
不偏推定量はこちら
|
|
18
|
+
```python3
|
|
19
|
+
import pandas as pd
|
|
20
|
+
import statistics
|
|
21
|
+
import numpy as np
|
|
22
|
+
|
|
23
|
+
df = pd.DataFrame([[1, 2], [1, 3], [4, 6]], columns=['A', 'B'])
|
|
24
|
+
data_list = df.values.tolist()
|
|
25
|
+
hensa = np.std(data_list, ddof=1)
|
|
26
|
+
print("標準偏差=",hensa)
|
|
27
|
+
# 標準偏差= 1.9407902170679516
|
|
15
28
|
```
|
1
コード修正
answer
CHANGED
|
@@ -9,7 +9,7 @@
|
|
|
9
9
|
|
|
10
10
|
df = pd.DataFrame([[1, 2], [1, 3], [4, 6]], columns=['A', 'B'])
|
|
11
11
|
data_list = df.values.tolist()
|
|
12
|
-
hensa = np.std(data_list
|
|
12
|
+
hensa = np.std(data_list)
|
|
13
13
|
print("標準偏差=",hensa)
|
|
14
|
-
# 標準偏差=
|
|
14
|
+
# 標準偏差= 1.7716909687891083
|
|
15
15
|
```
|