import pandas as pd
data = pd.read_csv("train.csv")

len(data)

data

import numpy as np
y_train = np.array(data.Insult)

y_train

text_train = data.Comment.tolist()

text_train[6]

data_test = pd.read_csv("test_with_solutions.csv")

text_test, y_test = data_test.Comment.tolist(), np.array(data_test.Insult)

from sklearn.feature_extraction.text import CountVectorizer

cv = CountVectorizer()
cv.fit(text_train)

len(cv.vocabulary_)

cv.vocabulary_

X_train = cv.transform(text_train)

X_train

text_train[6]

X_train[6, :].nonzero()[1]

X_test = cv.transform(text_test)

from sklearn.svm import LinearSVC
svm = LinearSVC(C=.01)

svm.fit(X_train, y_train)

svm.score(X_train, y_train)

svm.score(X_test, y_test)

coef = svm.coef_.ravel()
positive_coefficients = np.argsort(coef)[-25:]
negative_coefficients = np.argsort(coef)[:25]
interesting_coefficients = np.hstack([negative_coefficients, positive_coefficients])

%matplotlib inline
import matplotlib.pyplot as plt

plt.figure(figsize=(15, 5))
plt.bar(np.arange(50), coef[interesting_coefficients], color=["red" if c < 0 else "blue" for c in coef[interesting_coefficients]])
feature_names = np.array(cv.get_feature_names())
plt.xticks(np.arange(1, 51), feature_names[interesting_coefficients], rotation=60, ha="right");

from sklearn.pipeline import Pipeline

pipeline = Pipeline([('vectorizer', cv), ('classifier', svm)])

pipeline.fit(text_train, y_train)

pipeline.score(text_test, y_test)

from sklearn.grid_search import GridSearchCV

param_grid = {'classifier__C': 10. ** np.arange(-3, 3)}
grid_search = GridSearchCV(pipeline, param_grid=param_grid)

grid_search.fit(text_train, y_train)

grid_search.score(text_test, y_test)

param_grid = {'classifier__C': 10. ** np.arange(-3, 3), "vectorizer__ngram_range": [(1, 1), (1, 2), (1, 3), (2, 3), (2, 2)]}
grid_search = GridSearchCV(pipeline, param_grid=param_grid, n_jobs=3)

grid_search.fit(text_train, y_train)

grid_search.best_params_

grid_search.best_score_