import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
%matplotlib notebook

from sklearn.feature_extraction.text import CountVectorizer
from sklearn.linear_model import LogisticRegression
from sklearn.dummy import DummyClassifier
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.metrics import confusion_matrix

def add_feature(X, feature_to_add):
    """
    Returns sparse feature matrix with added feature.
    feature_to_add can also be a list of features.
    """
    from scipy.sparse import csr_matrix, hstack
    return hstack([X, csr_matrix(feature_to_add).T], 'csr')

df = pd.read_csv('./spam.csv')

df.head()

plt.figure(figsize=(8, 6))

x_axis = df['target'].unique()
y_axis = df['target'].value_counts()

plt.bar(x_axis, y_axis)
plt.show()