breast_cancer_data_set.py

#Read in the cancer data set
df = pd.read_csv('https://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer/breast-cancer.data', header=None)
#Declare the column names of the cancer data set
df.columns=["Class", "Age", "Menopause",
            "Tumor_Size", "Inv_Nodes", 
            "Node_Caps", "Deg_Malig",
            "Breast", "Breast_quad",
            "Irradiat"]
#Convert all of the categorical features variables to numeric (use LabelEncoder)
d = defaultdict(LabelEncoder)    
df_label_encoded = df.apply(lambda x: d[x.name].fit_transform(x))