test_df= pd.DataFrame({'Year': ['2012', '2013', '2014', '2015', '2012', '2013', '2014', '2015', '2012', '2013', '2014', '2015'],
                       'Theft': [100,200,300,230, 20,34,56, 65, 43,56,79,109],
                       'Robbery': [100,200,300,230, 20,34,56, 65, 43,56,79,109],
                       'Assult': [102,230,320,235, 201,343,90, 106, 143,156,179,102],
                     'Area': ['Chicago, IL metro area', 'Chicago, IL metro area', 'Chicago, IL metro area', 'Chicago, IL metro area', 'Chicago, IL', 'Chicago, IL', 'Chicago, IL', 'Chicago, IL', 'Chicago, IL - Albany Park', 'Chicago, IL - Albany Park', 'Chicago, IL - Albany Park', 'Chicago, IL - Albany Park'],
                     'yearly_sale_percentage': ['5%', '10%', '7%','21%', '15%', '12%', '2%','21%', '10%', '11%', '12%','6%'],
                     'price_status':[0, 1, 0,1,1,1,0,1,1,1,1,0]})

from sklearn.feature_extraction.text import TfidfVectorizer
vectorizer = TfidfVectorizer()

X= test_df.drop('price_status', axis=1)
X= vectorizer.fit_transform(X)
y= vectorizer.fit_transform(test_df['price_status'])

clf =  sklearn.svm.SVC(kernel=kernel)
clf.fit(X,y)