Guest User

Untitled

a guest
Dec 16th, 2018
114
0
Never
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 1.84 KB | None | 0 0
  1. Id Sequence
  2. 3 1,3,13...
  3. 7 1,2,1,...
  4. 8 1,2,4,...
  5. 11 1,8,25...
  6. 13 1,111,..
  7.  
  8. #Импортируем необходимые пакеты
  9. import sys
  10. import warnings
  11.  
  12. import pandas as pd
  13. import numpy as np
  14. from sklearn.metrics import mean_absolute_error, mean_squared_error
  15.  
  16. import statsmodels.formula.api as smf
  17. import statsmodels.tsa.api as smt
  18. import statsmodels.api as sm
  19. import scipy.stats as scs
  20. from scipy.optimize import minimize
  21.  
  22. import matplotlib.pyplot as plt
  23.  
  24. #читаем данные и выводим
  25. dftrain = pd.read_csv('../../data/IntegerSeqTrain.csv', sep=",", index_col=['Id'])
  26. dftrain.head(10)
  27.  
  28. Sequence
  29. Id
  30. 3 1,3,13...
  31. 7 1,2,1,...
  32. 8 1,2,4,...
  33. 11 1,8,25...
  34. 13 1,111,...
  35.  
  36. #для удобства пишем последовательности в столбец, предварительно разбив по запятой
  37.  
  38. print(dftrain.shape[1])
  39. i=0
  40. for dfitem in dftrain:
  41. j=0
  42. for dfitem2 in dfitem:
  43. dftrain[j] = dftrain['Sequence'].str.split(',').str.get(j)
  44. j+=1
  45. i+=1
  46. #удаляем лишний столбец
  47. dftrain = dftrain.drop('Sequence', 1)
  48. #pd.set_option('max_colwidth', 10)
  49. #что получилось
  50. print(dftrain.head(10))
  51.  
  52. 0 1 2 3 4 5 6 7
  53. Id
  54. 3 1 3 13 87 1053 28576 2141733 508147108
  55. 7 1 2 1 5 5 1 11 16
  56. 8 1 2 4 5 8 10 16 20
  57. 11 1 8 25 83 274 2275 132224 1060067
  58. 13 1 111 12211 1343211 147753211 162528... 178781... 196659...
  59. 15 1 1 1 1 1 1 1 1
  60. 16 840 1320 1680 2520 3192 3432 4920 5208
Add Comment
Please, Sign In to add comment