def show_all_scores():
X_orig, Y_orig = load_sanders_data()
unique_classes = np.unique(Y_orig)
for c in unique_classes:
print("#%s tweets: %i" % (c, sum(Y_orig == c)))
print(120 * "#")
print "== Pos vs. neg =="
pos_neg = np.logical_or(Y_orig == "positive", Y_orig == "negative")
X = X_orig[pos_neg]
Y = Y_orig[pos_neg]
Y = tweak_labels(Y, ["positive"])
train_and_evaluate(X, Y, name="pos vs neg")
print(120 * "#")
print "== Pos/neg vs. irrelevant/neutral =="
X = X_orig
Y = tweak_labels(Y_orig, ["positive", "negative"])
train_and_evaluate(X, Y, name="sentiment vs rest")
print(120 * "#")
print "== Pos vs. rest =="
X = X_orig
Y = tweak_labels(Y_orig, ["positive"])
train_and_evaluate(X, Y, name="pos vs rest")
print(120 * "#")
print "== Neg vs. rest =="
X = X_orig
Y = tweak_labels(Y_orig, ["negative"])
train_and_evaluate(X, Y, name="neg vs rest")
print(120 * "#")
def show_all_scores():
X_orig, Y_orig = load_sanders_data()
unique_classes = np.unique(Y_orig)
for c in unique_classes:
print ("#%s tweets: %i" % (c, sum(Y_orig == c)))
print (120 * "#")
print "== Pos vs. neg =="
pos_neg = np.logical_or(Y_orig == "positive", Y_orig == "negative")
X = X_orig[pos_neg]
Y = Y_orig[pos_neg]
Y = tweak_labels(Y, ["positive"])
# best_clf, best_score, best_params = grid_search_model(create_ngram_model, X, Y)
train_and_evaluate_tuned_model(X, Y, name="pos vs neg (tuned)")
print (120 * "#")
print "== Pos/neg vs. irrelevant/neutral =="
X = X_orig
Y = tweak_labels(Y_orig, ["positive", "negative"])
train_and_evaluate_tuned_model(X, Y, name="sentiment vs rest (tuned)")
print (120 * "#")
print "== Pos vs. rest =="
X = X_orig
Y = tweak_labels(Y_orig, ["positive"])
train_and_evaluate_tuned_model(X, Y, name="pos vs rest (tuned)")
print (120 * "#")
print "== Neg vs. rest =="
X = X_orig
Y = tweak_labels(Y_orig, ["negative"])
train_and_evaluate_tuned_model(X, Y, name="neg vs rest (tuned)")
print (120 * "#")
def show_all_scores():
X_orig, Y_orig = load_sanders_data()
unique_classes = np.unique(Y_orig)
for c in unique_classes:
print("#%s tweets: %i" % (c, sum(Y_orig == c)))
print(120 * "#")
print "== Pos vs. neg =="
pos_neg = np.logical_or(Y_orig == "positive", Y_orig == "negative")
X = X_orig[pos_neg]
Y = Y_orig[pos_neg]
Y = tweak_labels(Y, ["positive"])
# best_clf, best_score, best_params = grid_search_model(create_ngram_model, X, Y)
train_and_evaluate_tuned_model(X, Y, name="pos vs neg (tuned)")
print(120 * "#")
print "== Pos/neg vs. irrelevant/neutral =="
X = X_orig
Y = tweak_labels(Y_orig, ["positive", "negative"])
train_and_evaluate_tuned_model(X, Y, name="sentiment vs rest (tuned)")
print(120 * "#")
print "== Pos vs. rest =="
X = X_orig
Y = tweak_labels(Y_orig, ["positive"])
train_and_evaluate_tuned_model(X, Y, name="pos vs rest (tuned)")
print(120 * "#")
print "== Neg vs. rest =="
X = X_orig
Y = tweak_labels(Y_orig, ["negative"])
train_and_evaluate_tuned_model(X, Y, name="neg vs rest (tuned)")
print(120 * "#")
vect__min_df=1,
vect__stop_words=None,
vect__smooth_idf=False,
vect__use_idf=False,
vect__sublinear_tf=True,
vect__binary=False,
clf__alpha=0.01,
)
best_clf = create_ngram_model(best_params)
return best_clf
if __name__ == "__main__":
X_orig, Y_orig = load_sanders_data()
classes = np.unique(Y_orig)
for c in classes:
print("#%s: %i" % (c, sum(Y_orig == c)))
print("== Pos vs. neg ==")
pos_neg = np.logical_or(Y_orig == "positive", Y_orig == "negative")
X = X_orig[pos_neg]
Y = Y_orig[pos_neg]
Y = tweak_labels(Y, ["positive"])
train_model(get_best_model(), X, Y, name="pos vs neg", plot=True)
print("== Pos/neg vs. irrelevant/neutral ==")
X = X_orig
Y = tweak_labels(Y_orig, ["positive", "negative"])
best_params = dict(vect__ngram_range=(1, 2),
vect__min_df=1,
vect__stop_words=None,
vect__smooth_idf=False,
vect__use_idf=False,
vect__sublinear_tf=True,
vect__binary=False,
clf__alpha=0.01,
)
best_clf = create_ngram_model(best_params)
return best_clf
if __name__ == "__main__":
X_orig, Y_orig = load_sanders_data()
classes = np.unique(Y_orig)
for c in classes:
print "#%s: %i" % (c, sum(Y_orig == c))
print "== Pos vs. neg =="
pos_neg = np.logical_or(Y_orig == "positive", Y_orig == "negative")
X = X_orig[pos_neg]
Y = Y_orig[pos_neg]
Y = tweak_labels(Y, ["positive"])
train_model(get_best_model(), X, Y, name="pos vs neg", plot=True)
print "== Pos/neg vs. irrelevant/neutral =="
X = X_orig
Y = tweak_labels(Y_orig, ["positive", "negative"])
def sentimentAndNoSentiment(X,Y):
#Y now contains 1 for tweets that were positive or negative
#and 0 for neutral or irrelevant
Y= u.tweak_labels(Y,["positive","negative"])
classes = np.unique(Y)
for c in classes:
print("#%s: %i" % (c, sum(Y==c)))
train_model(Models.get_best_union_model,X,Y,"sentimentVsNoSentiment",True)
def posVsRest(X,Y):
#Y now contains 1 for tweets that were positive
#and 0 for negative, neutral or irrelevant
Y= u.tweak_labels(Y,["positive"])
classes = np.unique(Y)
for c in classes:
print("#%s: %i" % (c, sum(Y==c)))
train_model(Models.create_ngram_model,X,Y,"posVsRest",True)
def findBestEstimator(X,Y):
best_clf = gridSearchModel.grid_search_model(Models.create_ngram_model,X,Y)
X,Y = u.load_sanders_data()
runJustPosandNeg(X,Y)
#sentimentAndNoSentiment(X,Y)
#posVsRest(X,Y)
#find best estimator for sentiment vs no sentiment
#Y= u.tweak_labels(Y,["positive","negative"])
#findBestEstimator(X,Y)
