Machine Learning A-Z: Part 1 – Data Preprocessing
Python
|
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 |
# Data Preprocessing # Importing the libraries import numpy as np import matplotlib.pyplot as plt import pandas as pd # Importing the dataset dataset = pd.read_csv('Data.csv') X = dataset.iloc[:, :-1].values y = dataset.iloc[:, 3].values # Taking care of missing data from sklearn.preprocessing import Imputer imputer = Imputer(missing_values = 'NaN', strategy = 'mean', axis = 0) imputer = imputer.fit(X[:, 1:3]) X[:, 1:3] = imputer.transform(X[:, 1:3]) # Encoding categorical data from sklearn.preprocessing import LabelEncoder, OneHotEncoder labelencoder_X = LabelEncoder() X[:, 0] = labelencoder_X.fit_transform(X[:, 0]) onehotencoder = OneHotEncoder(categorical_features = [0]) X = onehotencoder.fit_transform(X).toarray() labelencoder_y = LabelEncoder() y = labelencoder_y.fit_transform(y) # Splitting the dataset into the Training set and Test set from sklearn.cross_validation import train_test_split X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 0) # Feature Scaling from sklearn.preprocessing import StandardScaler sc_X = StandardScaler() X_train = sc_X.fit_transform(X_train) X_test = sc_X.transform(X_test) |
To show full array.
R
|
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 |
# Data Preprocessing # Importing the dataset dataset = read.csv('Data.csv') # Taking care of missing data dataset$Age = ifelse(is.na(dataset$Age), ave(dataset$Age, FUN = function(x) mean(x, na.rm = TRUE)), dataset$Age) dataset$Salary = ifelse(is.na(dataset$Salary), ave(dataset$Salary, FUN = function(x) mean(x, na.rm = TRUE)), dataset$Salary) # Encoding categorical data dataset$Country = factor(dataset$Country, levels = c('France', 'Spain', 'Germany'), labels = c(1, 2, 3)) dataset$Purchased = factor(dataset$Purchased, levels = c('No', 'Yes'), labels = c(0, 1)) # Splitting the dataset into the Training set and Test set # install.packages('caTools') library(caTools) set.seed(123) split = sample.split(dataset$Purchased, SplitRatio = 0.8) training_set = subset(dataset, split == TRUE) test_set = subset(dataset, split == FALSE) # Feature Scaling training_set[, 2:3] = scale(training_set[, 2:3]) test_set[, 2:3] = scale(test_set[, 2:3]) |
