У меня есть справочная таблица, созданная с использованием -
lookupTable, data_training_panda_y_indexed = np.unique(data_training_panda_y, return_inverse=True)
Однако я хочу применить lookupTable к другому массиву data_cross_validation_panda_y
data_training_panda_y - это списокстроки, которые могут принимать эти значения - Входящие, Исходящие, Нейтральные.
Итак, lookUpTable - это ndArray ('Incoming' 'Outgoing 'Neutral')
Код на данный момент -
import numpy as np
import pandas as pd
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score
from numpy import dtype
from _codecs import lookup
#Load data
data = np.genfromtxt('../Data/bezdekIris.csv',delimiter=',',usecols=[0,1,2,3,4],dtype=None)
labels = np.genfromtxt('../Data/bezdekIris.csv',delimiter=',',usecols=[4],dtype=None)
#Shuffle the rows
np.random.shuffle(data)
#Cut the data into 3 parts
data_rows = np.size(data, 0)
training_rows = int(round(0.6*data_rows))
cross_validation_rows = int(round(0.2*data_rows))
testing_rows = data_rows - training_rows - cross_validation_rows
data_training_panda = pd.DataFrame(data[:training_rows])
data_training_panda_X = data_training_panda.iloc[:,0:4]
data_training_panda_y = data_training_panda.iloc[:,4]
data_cross_validation_panda = pd.DataFrame(data[training_rows:training_rows+cross_validation_rows])
data_cross_validation_panda_X = data_cross_validation_panda.iloc[:,0:4]
data_cross_validation_panda_y = data_cross_validation_panda.iloc[:,4]
data_testing_panda = pd.DataFrame(data[training_rows+cross_validation_rows:])
data_testing_panda_X = data_testing_panda.iloc[:,0:4]
data_testing_panda_y = data_testing_panda.iloc[:,4]
#Take out the labels from the 3 parts
lookupTable, data_training_panda_y_indexed = np.unique(data_training_panda_y, return_inverse=True)
#Label the CV and Testing
data_cross_validation_panda_y_indexed = np.array([])
data_testing_panda_y_indexed = np.array([])
bezdekIris.csvПример данных -
5.1,3.5,1.4,0.2,Incoming
4.9,3.0,1.4,0.2,Outgoing
4.7,3.2,1.3,0.2,Netural