Quadratic-Discriminant-Analysis.py

from sklearn.model_selection import train_test_split
from sklearn.model_selection import RepeatedStratifiedKFold
from sklearn.model_selection import cross_val_score
from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis 
from sklearn import datasets
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np

#load iris dataset
iris = datasets.load_iris()

#convert dataset to pandas DataFrame
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']

#view first six rows of DataFrame
df.head()

#find how many total observations are in dataset
len(df.index)

#define predictor and response variables
X = df[['s_length', 's_width', 'p_length', 'p_width']]
y = df['species']

#Fit the QDA model
model = QuadraticDiscriminantAnalysis()
model.fit(X, y)

#Define method to evaluate model
cv = RepeatedStratifiedKFold(n_splits=10, n_repeats=3, random_state=1)

#evaluate model
scores = cross_val_score(model, X, y, scoring='accuracy', cv=cv, n_jobs=-1)
print(np.mean(scores)) 

#define new observation
new = [5, 3, 1, .4]

#predict which class the new observation belongs to
model.predict([new])