def eval_by_labale(lable, docs, trained_data):
"""Calculate precision and recall and return it as dictionary structure
"""
corr_lab = [
(l, doc) for (l, doc) in docs if l == lable and lable == assignment1.classify_nb(trained_data, doc)
] # number of labeled docs which is correct
gss_lab = [
(l, doc) for (l, doc) in docs if lable == assignment1.classify_nb(trained_data, doc)
] # number of labeled docs which is correct
all_lab = [(l, doc) for (l, doc) in docs if l == lable] # number of labeled docs which is correct
return {"precision": len(corr_lab) / len(gss_lab), "recall": len(corr_lab) / len(all_lab)}
def eval_by_labale(lable, docs, trained_data):
"""Calculate precision and recall and return it as dictionary structure
"""
corr_lab = [
(l, doc) for (l, doc) in docs
if l == lable and lable == assignment1.classify_nb(trained_data, doc)
] # number of labeled docs which is correct
gss_lab = [(l, doc) for (l, doc) in docs
if lable == assignment1.classify_nb(trained_data, doc)
] # number of labeled docs which is correct
all_lab = [(l, doc) for (l, doc) in docs
if l == lable] # number of labeled docs which is correct
return {
"precision": len(corr_lab) / len(gss_lab),
"recall": len(corr_lab) / len(all_lab)
}
def cross_val(N=5):
"""Returns Returns a list of booleans that shows if classifier guess is correct or not
for whole test iterations
And it prints confidence interval of whole test iterations
N is number for iteration in document to divided to training and test parts
"""
all_docs = assignment1.read_corpus("all_sentiment_shuffled.txt")
all_docs = [(sentiment, doc) for (_, sentiment, doc) in all_docs]
results = []
for fold_nbr in range(N):
split_point_1 = int(float(fold_nbr) / N * len(all_docs))
split_point_2 = int(float(fold_nbr + 1) / N * len(all_docs))
train_docs = all_docs[:split_point_1] + all_docs[split_point_2:]
eval_docs = all_docs[split_point_1:split_point_2]
trained_data = assignment1.train_nb(train_docs)
for (s, d) in eval_docs:
results.append(s == assignment1.classify_nb(trained_data, d))
print acc_ci(results, 0.95)
return results
def cross_val(N=5):
"""Returns Returns a list of booleans that shows if classifier guess is correct or not
for whole test iterations
And it prints confidence interval of whole test iterations
N is number for iteration in document to divided to training and test parts
"""
all_docs = assignment1.read_corpus("all_sentiment_shuffled.txt")
all_docs = [(sentiment, doc) for (_, sentiment, doc) in all_docs]
results = []
for fold_nbr in range(N):
split_point_1 = int(float(fold_nbr) / N * len(all_docs))
split_point_2 = int(float(fold_nbr + 1) / N * len(all_docs))
train_docs = all_docs[:split_point_1] + all_docs[split_point_2:]
eval_docs = all_docs[split_point_1:split_point_2]
trained_data = assignment1.train_nb(train_docs)
for (s, d) in eval_docs:
results.append(s == assignment1.classify_nb(trained_data, d))
print acc_ci(results, 0.95)
return results
def classify(classifier):
"""Returns a list of booleans that shows if classifier guess is correct or not
classifier is either assignment1 or scikit classifier
"""
all_docs = assignment1.read_corpus("all_sentiment_shuffled.txt")
all_docs = [(sentiment, doc) for (_, sentiment, doc) in all_docs]
split_point = int(0.8 * len(all_docs))
results = []
train_docs = all_docs[:split_point]
eval_docs = all_docs[split_point:]
if classifier == "assignment1":
trained_data = assignment1.train_nb(train_docs)
for (s, d) in eval_docs:
results.append(s == assignment1.classify_nb(trained_data, d))
elif classifier == "scikit":
trained_data = ec.train_sk(train_docs)
for (s, d) in eval_docs:
results.append(s == ec.classify_sk(d, trained_data))
else:
print "Please set classifier as assignment1 or scikit"
return results
def classify(classifier):
"""Returns a list of booleans that shows if classifier guess is correct or not
classifier is either assignment1 or scikit classifier
"""
all_docs = assignment1.read_corpus("all_sentiment_shuffled.txt")
all_docs = [(sentiment, doc) for (_, sentiment, doc) in all_docs]
split_point = int(0.8 * len(all_docs))
results = []
train_docs = all_docs[:split_point]
eval_docs = all_docs[split_point:]
if classifier == "assignment1":
trained_data = assignment1.train_nb(train_docs)
for (s, d) in eval_docs:
results.append(s == assignment1.classify_nb(trained_data, d))
elif classifier == "scikit":
trained_data = ec.train_sk(train_docs)
for (s, d) in eval_docs:
results.append(s == ec.classify_sk(d, trained_data))
else:
print "Please set classifier as assignment1 or scikit"
return results