30 lines
809 B
Python
30 lines
809 B
Python
|
print('# statystyki dla pełnego zbioru')
|
||
|
|
|
||
|
|
import pandas as pd
|
||
|
|
plant_all = pd.read_csv('data/Plant_1_Generation_Data.csv')
|
||
|
|
print(plant_all.describe(include='all'))
|
||
|
|
|
||
|
|
print('# statystyki dla zbioru dev')
|
||
|
|
|
||
|
|
plant_dev = pd.read_csv('data/Plant_1_Generation_Data.csv.dev')
|
||
|
|
print(plant_dev.describe(include='all'))
|
||
|
|
|
||
|
|
print('# statystyki dla zbioru test')
|
||
|
|
|
||
|
|
plant_test = pd.read_csv('data/Plant_1_Generation_Data.csv.test')
|
||
|
|
print(plant_test.describe(include='all'))
|
||
|
|
|
||
|
|
print('# statystyki dla zbioru train')
|
||
|
|
|
||
|
|
plant_train = pd.read_csv('data/Plant_1_Generation_Data.csv.train')
|
||
|
|
print(plant_train.describe(include='all'))
|
||
|
|
|
||
|
|
print('# normalizacja')
|
||
|
|
|
||
|
|
|
||
|
|
plant_normalized = plant_test.copy()
|
||
|
|
column = 'DC_POWER'
|
||
|
|
|
||
|
|
plant_normalized[column] = plant_normalized[column] / plant_normalized[column].abs().max()
|
||
|
|
|
||
|
|
print(plant_normalized)
|