Análise Exploratório Projeto 7764

   issuekey  ... storypoints
0  29688087  ...           1
1  29682716  ...           1
2  29644971  ...           1
3  29494181  ...           1
4  29437529  ...           1

[5 rows x 5 columns]

(355, 5)

Este conjunto de dados tem 355 observações. Cada observação é uma User Story do Projeto 7764. O conjunto de dados tem 5 colunas.

   storypoints                                            context
0            1  Update templates for website merge requestsRel...
1            1  Make sure that we Capture Advanced Search in o...
2            1  Propose new IA for Brand and Digital Handbook#...
3            1  Cache `node_modules` for www-gitlab-com pipeli...
4            1  Disable all remaining unnecessary jobs in pipe...

    valures  Contagem
0         0         1
1         1       167
2         2        80
3         3        54
4         4        15
5         5        17
6         6         1
7         7         2
8         8         9
9        10         6
10       24         1
11       32         1
12      128         1

count    355.000000
mean       2.732394
std        7.186298
min        0.000000
25%        1.000000
50%        2.000000
75%        3.000000
max      128.000000
Name: storypoints, dtype: float64

A grande maioria das User Story. 75% da amostra foi medido como 1, 2 ou 3 Story Points.

<Figure size 800x600 with 0 Axes>
<AxesSubplot: >
Text(0.5, 1.0, 'Value Counts dos Story Points do Projeto 7764')
Text(0.5, 0, 'Valores do Story Point')
Text(0, 0.5, 'Contagem de vezes dos Story Points')

<Figure size 800x200 with 0 Axes>
{'whiskers': [<matplotlib.lines.Line2D object at 0x0000022113C614E0>, <matplotlib.lines.Line2D object at 0x0000022113C61780>], 'caps': [<matplotlib.lines.Line2D object at 0x0000022113C61A20>, <matplotlib.lines.Line2D object at 0x0000022113C61CC0>], 'boxes': [<matplotlib.lines.Line2D object at 0x0000022113C61240>], 'medians': [<matplotlib.lines.Line2D object at 0x0000022113C61F60>], 'fliers': [<matplotlib.lines.Line2D object at 0x0000022113C62200>], 'means': []}
Text(0.5, 1.0, 'Boxplot da Coluna Story Point')
Text(0.5, 0, 'Valores do Story Point')

Existem outliers nos Story Points, ou seja alguns Story Points são distantes da média mais do que 2 desvios padrão.

   storypoints                                            context
0            1  Update templates for website merge requestsRel...
1            1  Make sure that we Capture Advanced Search in o...
2            1  Propose new IA for Brand and Digital Handbook#...
3            1  Cache `node_modules` for www-gitlab-com pipeli...
4            1  Disable all remaining unnecessary jobs in pipe...

<Figure size 800x200 with 0 Axes>
{'whiskers': [<matplotlib.lines.Line2D object at 0x0000022113CAB790>, <matplotlib.lines.Line2D object at 0x0000022113CABA30>], 'caps': [<matplotlib.lines.Line2D object at 0x0000022113CABCD0>, <matplotlib.lines.Line2D object at 0x0000022113CABF70>], 'boxes': [<matplotlib.lines.Line2D object at 0x0000022113CAB4F0>], 'medians': [<matplotlib.lines.Line2D object at 0x0000022113CD8250>], 'fliers': [<matplotlib.lines.Line2D object at 0x0000022113CD84F0>], 'means': []}
Text(0.5, 1.0, 'Boxplot dos Story Points do Projeto 7764 depois da remoção dos outliers')

<Figure size 800x600 with 0 Axes>
<AxesSubplot: >
Text(0.5, 1.0, 'Value Counts dos Story Points do Projeto 7764')
Text(0.5, 0, 'Valores do Story Point')
Text(0, 0.5, 'Contagem de vezes dos Story Points')

2.158536585365854

A média de Story Point de todo o conjunto de dados é de 2.15 Story Point

1.3193741371375978

o MAE é de 1.31, quando utilizamos a média dos Story Points. Ou seja, o Erro médo absoluto é de 1.28 SP quando sempre utilizamos um valor fixo, lembrando que foi utilizado todo o conjunto de dados.

  modelo  MAE Teste color
0  Media   1.319374  blue

df_results

<string>:1: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
<string>:1: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
<string>:1: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
<string>:1: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
<string>:1: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
<string>:1: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

SVR()

<string>:1: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.

           modelo  MAE Teste   color
0           Media   1.319374    blue
1  Legibility SVM   1.221740  orange

O MAE do modelo preditivo legibility é menor do que o MAE, quando utilizamos a média dos Story Poits.

SVR()

<string>:1: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.

           modelo  MAE Teste   color
0           Media   1.319374    blue
1  Legibility SVM   1.221740  orange
2      TF-IDF SVM   1.270728   green

<Figure size 640x480 with 0 Axes>
<BarContainer object of 3 artists>
Text(0.5, 1.0, 'Comparação do MAE entre os modelos')
Text(0.5, 0, 'Modelos')
Text(0, 0.5, 'MAE')
(1.1, 1.4)