Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- Id Sequence
- 3 1,3,13...
- 7 1,2,1,...
- 8 1,2,4,...
- 11 1,8,25...
- 13 1,111,..
- #Импортируем необходимые пакеты
- import sys
- import warnings
- import pandas as pd
- import numpy as np
- from sklearn.metrics import mean_absolute_error, mean_squared_error
- import statsmodels.formula.api as smf
- import statsmodels.tsa.api as smt
- import statsmodels.api as sm
- import scipy.stats as scs
- from scipy.optimize import minimize
- import matplotlib.pyplot as plt
- #читаем данные и выводим
- dftrain = pd.read_csv('../../data/IntegerSeqTrain.csv', sep=",", index_col=['Id'])
- dftrain.head(10)
- Sequence
- Id
- 3 1,3,13...
- 7 1,2,1,...
- 8 1,2,4,...
- 11 1,8,25...
- 13 1,111,...
- #для удобства пишем последовательности в столбец, предварительно разбив по запятой
- print(dftrain.shape[1])
- i=0
- for dfitem in dftrain:
- j=0
- for dfitem2 in dfitem:
- dftrain[j] = dftrain['Sequence'].str.split(',').str.get(j)
- j+=1
- i+=1
- #удаляем лишний столбец
- dftrain = dftrain.drop('Sequence', 1)
- #pd.set_option('max_colwidth', 10)
- #что получилось
- print(dftrain.head(10))
- 0 1 2 3 4 5 6 7
- Id
- 3 1 3 13 87 1053 28576 2141733 508147108
- 7 1 2 1 5 5 1 11 16
- 8 1 2 4 5 8 10 16 20
- 11 1 8 25 83 274 2275 132224 1060067
- 13 1 111 12211 1343211 147753211 162528... 178781... 196659...
- 15 1 1 1 1 1 1 1 1
- 16 840 1320 1680 2520 3192 3432 4920 5208
Add Comment
Please, Sign In to add comment