from classifiers import Classifier
from db import DataManager
N_TIMES = 1
for i in range(0,N_TIMES):
print i+1, "times"
DATABASE = "us_twitter.db"
split = 0.8
db_mgr = DataManager(DATABASE)
train_tweets, train_labels = db_mgr.select_wikipedia_train()
test_tweets, test_labels, dummy1, dummy2 = db_mgr.select_tweets(limit=10, state_fips=True, table="us_tweets", label=state_fips)
results = get("results.json")
vectorizer = get_vectorizer("tfidf", min_df=1)
classifiers = {
"BernoulliNB": Classifier(classifier="bnb"),
"MultinomialNB": Classifier(classifier="nb"),
"KNN-1000": Classifier(classifier="knn", k=1000),
"KNN-2000": Classifier(classifier="knn", k=2000),
# "SVC": Classifier(classifier="svm", params={"C" : 1.0,"kernel" : 'linear','verbose':True})
"SVC": Classifier(load="classifier-SVC")
}
# Vectorizing Training Data
# ["tweets", "preprocess", "grid_5_label",grid_5_degree,True],
# ["tweets", "preprocess", "grid_10_label",grid_10_degree,True]
]
for p in range(0,len(params)):
print params[p]
TRAINING, PREPROCESSING, LABEL_FUNC, label_func, preprocess = params[p]
for i in range(0,N_TIMES):
print i+1, "times"
DATABASE = "us_twitter.db"
split = 0.8
db_mgr = DataManager(DATABASE)
if TRAINING == "tweets":
train_tweets, train_labels, test_tweets, test_labels = db_mgr.select_tweets(limit=SIZE, preprocess=preprocess, table="us_tweets", split=0.8, label=label_func)
else:
train_tweets, train_labels = db_mgr.select_wikipedia_train()
test_tweets, test_labels, dummy1, dummy2 = db_mgr.select_tweets(limit=(SIZE * 0.2), state_fips=True, table="us_tweets", label=label_func)
# print "Train Size:", len(train_tweets)
# print "Test Size:", len(test_tweets)
vectorizer = get_vectorizer(VECTORIZER, min_df=1)
classifiers = {
"BernoulliNB": Classifier(classifier="bnb"),
"MultinomialNB": Classifier(classifier="nb"),
# "KNN-50": Classifier(classifier="knn", k=50),
# "KNN-100": Classifier(classifier="knn", k=100),
# "KNN-1000": Classifier(classifier="knn", k=1000),
