Cargando las librerías necesarias.
#LOAD NECESSARY LIBRARIES
from sklearn.model_selection import train_test_split
from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis
from sklearn.model_selection import RepeatedStratifiedKFold
from sklearn.model_selection import cross_val_score
from sklearn import datasets
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
Cargando y viendo el iris dataset.
#LOAD AND VIEW IRIS DATASET
iris = datasets.load_iris()
df = pd.DataFrame(data = np.c_[iris['data'], iris['target']],
columns = iris['feature_names'] + ['target'])
df['species'] = pd.Categorical.from_codes(iris.target, iris.target_names)
df.columns = ['s_length', 's_width', 'p_length', 'p_width', 'target', 'species']
print(df.head())
## s_length s_width p_length p_width target species
## 0 5.1 3.5 1.4 0.2 0.0 setosa
## 1 4.9 3.0 1.4 0.2 0.0 setosa
## 2 4.7 3.2 1.3 0.2 0.0 setosa
## 3 4.6 3.1 1.5 0.2 0.0 setosa
## 4 5.0 3.6 1.4 0.2 0.0 setosa
len(df.index)
## 150
Definiendo el predictor y las variables respuesta.
#DEFINE PREDICTOR AND RESPONSE VARIABLES
X = df[['s_length', 's_width', 'p_length', 'p_width']]
y = df['species']
Estimando el modelo Discriminante Cuadrático.
#FIT LDA MODEL
model = QuadraticDiscriminantAnalysis()
model.fit(X, y)
## QuadraticDiscriminantAnalysis()
Definiendo el modelo a evaluar.
#DEFINE METHOD TO EVALUATE MODEL
cv = RepeatedStratifiedKFold(n_splits=10, n_repeats=3, random_state=1)
Evaluando el modelo
#EVALUATE MODEL
#scores = cross_val_score(model, X, y, scoring='accuracy', cv=cv, n_jobs=-1)
#print(np.mean(scores))
Usando el modelo para predecir una nueva observación.
#USE MODEL TO MAKE PREDICTION ON NEW OBSERVATION
new = [5, 3, 1, .4]
model.predict([new])
## array(['setosa'], dtype=object)