muffinvscupcake.py

import pandas as pd
import numpy as np
from sklearn import svm
import matplotlib.pyplot as plt
import seaborn as sns; sns.set(font_scale=1.2)

 
#load data
recipes=pd.read_csv('recipes_muffins_cupcakes.csv')

#plot data as two ingredients on two axes
sns.lmplot('Flour', 'Sugar', data=recipes, hue='Type',
           palette='Set1', fit_reg=False, scatter_kws={"s": 70});

#model inputs		   
ingredients = recipes[['Flour','Sugar']].as_matrix()
type_label = np.where(recipes['Type']=='Muffin', 0, 1)
recipe_features = recipes.columns.values[1:].tolist()		

#now we are fitting the svm model using sklearn's svc 
model = svm.SVC(kernel='linear')
model.fit(ingredients, type_label)

#visualise the hyperplanes
# Get the separating hyperplane
w = model.coef_[0]
a = -w[0] / w[1]
xx = np.linspace(30, 60)
yy = a * xx - (model.intercept_[0]) / w[1]

# Plot the parallels to the separating hyperplane that pass through the support vectors
b = model.support_vectors_[0]
yy_down = a * xx + (b[1] - a * b[0])
b = model.support_vectors_[-1]
yy_up = a * xx + (b[1] - a * b[0])

#now we will plot the hyperplane
sns.lmplot('Flour', 'Sugar', data=recipes, hue='Type', palette='Set1', fit_reg=False, scatter_kws={"s": 70})
plt.plot(xx, yy, linewidth=2, color='black');


#we know that the best hyperplane is the one with max margin
sns.lmplot('Flour', 'Sugar', data=recipes, hue='Type', palette='Set1', fit_reg=False, scatter_kws={"s": 70})
plt.plot(xx, yy, linewidth=2, color='black')
plt.plot(xx, yy_down, 'k--')
plt.plot(xx, yy_up, 'k--')
plt.scatter(model.support_vectors_[:, 0], model.support_vectors_[:, 1],
            s=80, facecolors='none');
			
			
#predict function
def muffin_or_cupcake(flour, sugar):
    if(model.predict([[flour, sugar]]))==0:
        print('muffin')
    else:
        print('cupcake')
		

# Predict if 50 parts flour and 20 parts sugar, for example
muffin_or_cupcake(50, 20) 
#outputs 'muffin'

"""
Pickling is just serialization: putting data into a form that can be stored in a file and retrieved later. Pickling is a way to convert a python object (list, dict, etc.) into a character stream. The idea is that this character stream contains all the information necessary to reconstruct the object in another python script.
"""