def getAllPhraseRankings(directions_fn=None, vectors_fn=None, property_names_fn=None, vector_names_fn=None, fn="no filename",
percentage_increment=1, scores_fn = None, top_amt=0, discrete=False, data_type="movies",
rewrite_files=False):
rankings_fn_all = "../data/" + data_type + "/rank/numeric/" + fn + "ALL.txt"
all_fns = [rankings_fn_all]
if dt.allFnsAlreadyExist(all_fns) and not rewrite_files:
print("Skipping task", "getAllPhraseRankings")
return
else:
print("Running task", "getAllPhraseRankings")
directions = dt.import2dArray(directions_fn)
vectors = dt.import2dArray(vectors_fn)
property_names = dt.import1dArray(property_names_fn)
vector_names = dt.import1dArray(vector_names_fn)
if top_amt != 0:
scores = dt.import1dArray(scores_fn, "f")
directions = dt.sortByReverseArray(directions, scores)[:top_amt]
property_names = dt.sortByReverseArray(property_names, scores)[:top_amt]
rankings = getRankings(directions, vectors, property_names, vector_names)
if discrete:
discrete_labels = createDiscreteLabels(rankings, percentage_increment)
discrete_labels = np.asarray(discrete_labels)
for a in range(len(rankings)):
rankings[a] = np.around(rankings[a], decimals=4)
#dt.write1dArray(property_names, "../data/movies/bow/names/top5kof17k.txt")
dt.write2dArray(rankings, rankings_fn_all)
def splitDirections(directions_fn, scores_fn, names_fn, is_gini,
amt_high_directions, amt_low_directions, high_threshold,
low_threshold, half_kappa_half_ndcg):
directions = np.asarray(dt.import2dArray(directions_fn))
scores = np.asarray(dt.import1dArray(scores_fn, "f"))
names = np.asarray(dt.import1dArray(names_fn))
high_direction_names = []
low_direction_names = []
high_directions = []
low_directions = []
if len(half_kappa_half_ndcg) > 0:
kappa_scores = dt.import1dArray(half_kappa_half_ndcg, "f")
if amt_high_directions > 0 and amt_low_directions > 0:
if len(half_kappa_half_ndcg) == 0:
ids = np.flipud(np.argsort(scores))
else:
ind1 = np.flipud(np.argsort(scores))[:amt_low_directions / 2]
ind2 = np.zeros(len(ind1), dtype="int")
kappa_scores = np.flipud(np.argsort(kappa_scores))
count = 0
added = 0
for i in kappa_scores:
if i not in ind1:
ind2[added] = i
added += 1
if added >= amt_low_directions / 2:
break
count += 1
shuffle_ind = np.asarray(list(range(0, len(ind1))))
ids = np.insert(ind1, shuffle_ind, ind2)
names = names[ids]
if max(ids) > len(directions):
directions = np.asarray(directions).transpose()
directions = directions[ids]
high_directions = directions[:amt_high_directions]
low_directions = directions[amt_high_directions:amt_low_directions]
high_direction_names = names[:amt_high_directions]
low_direction_names = names[amt_high_directions:amt_low_directions]
high_directions = high_directions.tolist()
low_directions = low_directions.tolist()
high_direction_names = high_direction_names.tolist()
low_direction_names = low_direction_names.tolist()
elif high_threshold > 0 and low_threshold > 0:
for s in range(len(scores)):
if scores[s] >= high_threshold:
high_directions.append(directions[s])
high_direction_names.append(names[s])
elif scores[s] >= low_threshold:
low_directions.append(directions[s])
low_direction_names.append(names[s])
else:
print("no thresholds or direction amounts")
hi = [None]
li = [None]
return high_direction_names, low_direction_names, high_directions, low_directions
def saveClusters(directions_fn,
scores_fn,
names_fn,
filename,
amt_of_dirs,
data_type,
cluster_amt,
rewrite_files=False,
algorithm="meanshift_k"):
dict_fn = "../data/" + data_type + "/cluster/dict/" + filename + ".txt"
cluster_directions_fn = "../data/" + data_type + "/cluster/clusters/" + filename + ".txt"
all_fns = [dict_fn]
if dt.allFnsAlreadyExist(all_fns) and not rewrite_files:
print("Skipping task", saveClusters.__name__)
return
else:
print("Running task", saveClusters.__name__)
p_dir = dt.import2dArray(directions_fn)
p_names = dt.import1dArray(names_fn, "s")
p_scores = dt.import1dArray(scores_fn, "f")
ids = np.argsort(p_scores)
p_dir = np.flipud(p_dir[ids])[:amt_of_dirs]
p_names = np.flipud(p_names[ids])[:amt_of_dirs]
if algorithm == "meanshift":
labels = meanShift(p_dir)
else:
labels = kMeans(p_dir, cluster_amt)
unique, counts = np.unique(labels, return_counts=True)
clusters = []
dir_clusters = []
for i in range(len(unique)):
clusters.append([])
dir_clusters.append([])
for i in range(len(labels)):
clusters[labels[i]].append(p_names[i])
dir_clusters[labels[i]].append(p_dir[i])
cluster_directions = []
for l in range(len(dir_clusters)):
cluster_directions.append(dt.mean_of_array(dir_clusters[l]))
print("------------------------")
for c in clusters:
print(c)
print("------------------------")
dt.write2dArray(clusters, dict_fn)
dt.write2dArray(cluster_directions, cluster_directions_fn)
def makePPMI(names_fn, scores_fn, amt, data_type, ppmi_fn, name_fn):
scores = np.asarray(dt.import1dArray(scores_fn, "f"))
names = np.asarray(dt.import1dArray(names_fn))
names = names[np.flipud(np.argsort(scores))][:amt]
if dt.allFnsAlreadyExist([ppmi_fn, name_fn]) is False:
ppmi_file = []
for name in names:
ppmi_file.append(
dt.import1dArray("../data/" + data_type + "/bow/ppmi/" +
"class-" + name + "-100-10-all"))
dt.write2dArray(ppmi_file, ppmi_fn)
dt.write1dArray(names, name_fn)
else:
print("already_made PPMI of this size")
def runSVM(self, property_name, y=None):
if y is None:
y = dt.import1dArray(
"../data/" + self.data_type + "/bow/binary/phrases/class-" +
property_name + "-" + str(self.lowest_amt) + "-" +
str(self.higher_amt) + "-" + self.classification,
file_type="i")
else:
y = y[0]
for i in range(len(y)):
if y[i] >= 1:
y[i] = 1
#x_train, y_train = dt.balanceClasses(x_train, y_train)
clf = svm.LinearSVC(class_weight="balanced", dual=False)
#if len(self.x_train) !=
clf.fit(self.x_train, y)
direction = clf.coef_.tolist()[0]
y_pred = clf.predict(self.x_test)
y_pred = y_pred.tolist()
f1 = f1_score(y[:len(y_pred)], y_pred)
kappa_score = cohen_kappa_score(y[:len(y_pred)], y_pred)
acc = accuracy_score(y[:len(y_pred)], y_pred)
TP, FP, TN, FN = self.perf_measure(y, y_pred)
print("TP", TP, "FP", FP, "TN", TN, "FN", FN)
return kappa_score, f1, direction, acc, 0, TP, FP, TN, FN
def runLR(self, property_name, y=None):
if y is None:
y = dt.import1dArray(
"../data/" + self.data_type + "/bow/binary/phrases/class-" +
property_name + "-" + str(self.lowest_amt) + "-" +
str(self.higher_amt) + "-" + self.classification,
file_type="i")
else:
y = y[0]
for i in range(len(y)):
if y[i] >= 1:
y[i] = 1
#x_train, y_train = dt.balanceClasses(x_train, y_train)
clf = linear_model.LogisticRegression(class_weight="balanced",
dual=False)
clf.fit(self.x_train, y)
direction = clf.coef_.tolist()[0]
y_pred = clf.predict(self.x_test)
y_pred = y_pred.tolist()
f1 = f1_score(y[:len(y_pred)], y_pred)
kappa_score = cohen_kappa_score(y[:len(y_pred)], y_pred)
acc = accuracy_score(y[:len(y_pred)], y_pred)
TP, FP, TN, FN = self.perf_measure(y, y_pred)
#ppmi_score, ppmi_ratio = get_ppmi_score(y_pred, property_name)
return kappa_score, f1, direction, acc, 0, TP, FP, TN, FN
def fixCutoffFormatting(cutoff_fn, file_name):
cutoff = dt.import1dArray(cutoff_fn)
cluster_dict = dt.readArrayDict(cluster_dict_fn)
for c in range(len(cutoff)):
cutoff[c] = cutoff[c].split()
for i in range(len(cutoff[c])):
cutoff[c][i] = int(dt.stripPunctuation(cutoff[c][i]))
dt.write2dArray(cutoff, "../data/movies/rules/cutoff/" +file_name+ ".txt")
def getAllRankings(directions_fn, vectors_fn, cluster_names_fn, vector_names_fn, percent, percentage_increment, by_vector, fn, discrete=True, data_type="movies",
rewrite_files=False):
#labels_fn = "../data/"+data_type+"/rank/labels/" + fn + ".txt"
rankings_fn = "../data/"+data_type+"/rank/numeric/" + fn + ".txt"
#discrete_labels_fn = "../data/"+data_type+"/rank/discrete/" + fn + ".txt"
all_fns = [rankings_fn]
if dt.allFnsAlreadyExist(all_fns) and not rewrite_files:
for f in all_fns:
print(f, "Already exists")
print("Skipping task", "getAllRankings")
return
else:
print("Running task", "getAllRankings")
directions = dt.import2dArray(directions_fn)
vectors = dt.import2dArray(vectors_fn)
cluster_names = dt.import1dArray(cluster_names_fn)
vector_names = dt.import1dArray(vector_names_fn)
rankings = getRankings(directions, vectors, cluster_names, vector_names)
rankings = np.asarray(rankings)
if discrete:
labels = createLabels(rankings, percent)
labels = np.asarray(labels)
discrete_labels = createDiscreteLabels(rankings, percentage_increment)
discrete_labels = np.asarray(discrete_labels)
if by_vector:
labels = labels.transpose()
if discrete:
discrete_labels = discrete_labels.transpose()
rankings = rankings.transpose()
if discrete:
dt.write2dArray(labels, labels_fn)
dt.write2dArray(rankings, rankings_fn)
if discrete:
dt.write2dArray(discrete_labels, discrete_labels_fn)
def getNDCG(rankings_fn,
fn,
data_type,
bow_fn,
ppmi_fn,
lowest_count,
rewrite_files=False,
highest_count=0,
classification=""):
# Check if the NDCG scores have already been calculated, if they have then skip.
ndcg_fn = "../data/" + data_type + "/ndcg/" + fn + ".txt"
all_fns = [ndcg_fn]
if dt.allFnsAlreadyExist(all_fns) and not rewrite_files:
print("Skipping task", getNDCG.__name__)
return
else:
print("Running task", getNDCG.__name__)
# Get the file names for the PPMI values for every word and a list of words ("names")
names = dt.import1dArray("../data/" + data_type + "/bow/names/" + bow_fn)
ppmi = dt.import2dArray("../data/" + data_type + "/bow/ppmi/" + ppmi_fn)
# Process the rankings and the PPMI line-by-line so as to not run out of memory
ndcg_a = []
#spearman_a = []
with open(rankings_fn) as rankings:
r = 0
for lr in rankings:
for lp in ppmi:
# Get the plain-number ranking of the rankings, e.g. "1, 4, 3, 50"
sorted_indices = np.argsort(
list(map(float,
lr.strip().split())))[::-1]
# Convert PPMI scores to floats
# Get the NDCG score for the PPMI score, which is a valuation, compared to the indice of the rank
ndcg = ndcg_from_ranking(lp, sorted_indices)
# Add to array and print
ndcg_a.append(ndcg)
print("ndcg", ndcg, names[r], r)
"""
smr = spearmanr(ppmi_indices, sorted_indices)[1]
spearman_a.append(smr)
print("spearman", smr, names[r], r)
"""
r += 1
break
# Save NDCG
dt.write1dArray(ndcg_a, ndcg_fn)
def runSVM(self, property_name):
y = dt.import1dArray("../data/" + self.data_type +
"/bow/binary/phrases/class-" + property_name +
"-" + str(self.lowest_amt) + "-" +
str(self.higher_amt) + "-" + self.classification)
#x_train, y_train = dt.balanceClasses(x_train, y_train)
clf = svm.LinearSVC(class_weight="balanced")
clf.fit(self.x_train, y)
direction = clf.coef_.tolist()[0]
y_pred = clf.predict(self.x_test)
y_pred = y_pred.tolist()
f1 = 0.0
kappa_score = cohen_kappa_score(y, y_pred)
ktau = 0.0
#ppmi_score, ppmi_ratio = get_ppmi_score(y_pred, property_name)
return kappa_score, f1, direction, 0, 0
plt.plot()
plt.savefig("../data/movies/figures/description.png", bbox_inches="tight")
plt.show()
y = ax.spines['bottom']
print(y)
dir_ids = [212,368]
classes = ["horror", "comedy"]
# Create direction graph
file_name = "f200geE300DS[200]DN0.5CTgenresHAtanhCV1 S0 SFT0 allL0"
cluster_fn = "100ndcg KMeans CA400 MC1 MS0.4 ATS1000 DS400"
class1 = np.asarray(dt.import1dArray("../data/movies/classify/genres/class-" + classes[0]), "i")
class2 = np.asarray(dt.import1dArray("../data/movies/classify/genres/class-" + classes[1]), "i")
top_indexes = dt.import1dArray("../data/movies/top_250_imdb.txt")
data_type = "movies"
directions = dt.import2dArray("../data/"+data_type+"/cluster/clusters/" + file_name + cluster_fn + ".txt")
d_names = dt.import1dArray("../data/"+data_type+"/cluster/names/" + file_name + cluster_fn + ".txt")
entities = np.asarray(dt.import2dArray("../data/"+data_type+"/nnet/spaces/"+file_name+".txt"))
e_names = np.asarray(dt.import1dArray("../data/" +data_type+"/nnet/spaces/entitynames.txt"))
class1 = class1[top_indexes]
class2 = class2[top_indexes]
confirmed_indexes = []
def __init__(self,
vector_path,
class_path,
property_names_fn,
file_name,
svm_type,
training_size=10000,
lowest_count=200,
highest_count=21470000,
get_kappa=True,
get_f1=True,
single_class=True,
data_type="movies",
getting_directions=True,
threads=1,
chunk_amt=0,
chunk_id=0,
rewrite_files=False,
classification="all",
loc="../data/"):
self.get_kappa = True
self.get_f1 = get_f1
self.data_type = data_type
self.classification = classification
self.lowest_amt = lowest_count
self.higher_amt = highest_count
if chunk_amt > 0:
file_name = file_name + " CID" + str(chunk_id) + " CAMT" + str(
chunk_amt)
directions_fn = loc + data_type + "/svm/directions/" + file_name + ".txt"
ktau_scores_fn = loc + data_type + "/svm/f1/" + file_name + ".txt"
kappa_fn = loc + data_type + "/svm/kappa/" + file_name + ".txt"
acc_fn = loc + data_type + "/svm/acc/" + file_name + ".txt"
all_fns = [directions_fn, kappa_fn]
if dt.allFnsAlreadyExist(all_fns) and not rewrite_files:
print("Skipping task", "getSVMResults")
return
else:
print("Running task", "getSVMResults")
y_train = 0
y_test = 0
vectors = np.asarray(dt.import2dArray(vector_path))
print("imported vectors")
if not getting_directions:
classes = np.asarray(dt.import2dArray(class_path))
print("imported classes")
property_names = dt.import1dArray(property_names_fn)
print("imported propery names")
if chunk_amt > 0:
if chunk_id == chunk_amt - 1:
chunk = int(len(property_names) / chunk_amt)
multiply = chunk_amt - 1
property_names = property_names[chunk * multiply:]
else:
property_names = dt.chunks(
property_names, int(
(len(property_names) / chunk_amt)))[chunk_id]
if not getting_directions:
x_train, x_test, y_train, y_test = train_test_split(vectors,
classes,
test_size=0.3,
random_state=0)
else:
x_train = vectors
x_test = vectors
if get_f1:
y_train = y_train.transpose()
y_test = y_test.transpose()
print("transpoosed")
self.x_train = x_train
self.x_test = x_test
self.y_train = y_train
self.y_test = y_test
if self.get_f1 is False:
print("running svms")
kappa_scores, directions, ktau_scores, property_names = self.runAllSVMs(
y_test, y_train, property_names, file_name, svm_type,
getting_directions, threads)
dt.write1dArray(kappa_scores, kappa_fn)
dt.write2dArray(directions, directions_fn)
dt.write1dArray(ktau_scores, ktau_scores_fn)
dt.write1dArray(property_names,
property_names_fn + file_name + ".txt")
else:
final_f1 = []
final_acc = []
for y in range(len(y_train)):
f1, acc = self.runClassifySVM(y_test[y], y_train[y])
print(f1, acc)
final_f1.append(f1)
final_acc.append(acc)
dt.write1dArray(final_f1, ktau_scores_fn)
dt.write1dArray(final_acc, acc_fn)
def __init__(self,
features_fn,
classes_fn,
class_names_fn,
cluster_names_fn,
filename,
max_depth=None,
balance=None,
criterion="entropy",
save_details=False,
data_type="movies",
cv_splits=5,
csv_fn="../data/temp/no_csv_provided.csv",
rewrite_files=True,
split_to_use=-1,
development=False,
limit_entities=False,
limited_label_fn=None,
vector_names_fn=None,
pruning=1,
save_results_so_far=False):
vectors = np.asarray(dt.import2dArray(features_fn)).transpose()
labels = np.asarray(dt.import2dArray(classes_fn, "i"))
print("vectors", len(vectors), len(vectors[0]))
print("labels", len(labels), len(labels[0]))
print("vectors", len(vectors), len(vectors[0]))
cluster_names = dt.import1dArray(cluster_names_fn)
label_names = dt.import1dArray(class_names_fn)
all_fns = []
file_names = ['ACC J48' + filename, 'F1 J48' + filename]
acc_fn = '../data/' + data_type + '/rules/tree_scores/' + file_names[
0] + '.scores'
f1_fn = '../data/' + data_type + '/rules/tree_scores/' + file_names[
1] + '.scores'
all_fns.append(acc_fn)
all_fns.append(f1_fn)
all_fns.append(csv_fn)
print(dt.allFnsAlreadyExist(all_fns), rewrite_files)
if dt.allFnsAlreadyExist(
all_fns) and not rewrite_files or save_results_so_far:
print("Skipping task", "Weka Tree")
return
else:
print("Running task", "Weka Tree")
for l in range(len(cluster_names)):
cluster_names[l] = cluster_names[l].split()[0]
"""
for l in range(len(label_names)):
if label_names[l][:6] == "class-":
label_names[l] = label_names[l][6:]
"""
f1_array = []
accuracy_array = []
labels = labels.transpose()
print("labels transposed")
print("labels", len(labels), len(labels[0]))
if limit_entities is False:
vector_names = dt.import1dArray(vector_names_fn)
limited_labels = dt.import1dArray(limited_label_fn)
vectors = np.asarray(
dt.match_entities(vectors, limited_labels, vector_names))
all_y_test = []
all_predictions = []
for l in range(len(labels)):
if balance:
new_vectors, new_labels = dt.balanceClasses(vectors, labels[l])
else:
new_vectors = vectors
new_labels = labels[l]
# Select training data with cross validation
ac_y_test = []
ac_y_train = []
ac_x_train = []
ac_x_test = []
ac_y_dev = []
ac_x_dev = []
cv_f1 = []
cv_acc = []
if cv_splits == 1:
kf = KFold(n_splits=3, shuffle=False, random_state=None)
else:
kf = KFold(n_splits=cv_splits,
shuffle=False,
random_state=None)
c = 0
for train, test in kf.split(new_vectors):
if split_to_use > -1:
if c != split_to_use:
c += 1
continue
ac_y_test.append(new_labels[test])
ac_y_train.append(new_labels[train[int(len(train) * 0.2):]])
val = int(len(train) * 0.2)
t_val = train[val:]
nv_t_val = new_vectors[t_val]
ac_x_train.append(nv_t_val)
ac_x_test.append(new_vectors[test])
ac_x_dev.append(new_vectors[train[:int(len(train) * 0.2)]])
ac_y_dev.append(new_labels[train[:int(len(train) * 0.2)]])
c += 1
if cv_splits == 1:
break
predictions = []
rules = []
if development:
ac_x_test = np.copy(np.asarray(ac_x_dev))
ac_y_test = np.copy(np.asarray(ac_y_dev))
train_fn = "../data/" + data_type + "/weka/data/" + filename + "Train.txt"
test_fn = "../data/" + data_type + "/weka/data/" + filename + "Test.txt"
for splits in range(len(ac_y_test)):
# Get the weka predictions
dt.writeArff(ac_x_train[splits], [ac_y_train[splits]],
[label_names[splits]],
train_fn,
header=True)
dt.writeArff(ac_x_test[splits], [ac_y_test[splits]],
[label_names[splits]],
test_fn,
header=True)
prediction, rule = self.getWekaPredictions(
train_fn + label_names[splits] + ".arff",
test_fn + label_names[splits] + ".arff", save_details,
pruning)
predictions.append(prediction)
rules.append(rule)
for i in range(len(predictions)):
if len(predictions) == 1:
all_y_test.append(ac_y_test[i])
all_predictions.append(predictions[i])
f1 = f1_score(ac_y_test[i], predictions[i], average="binary")
accuracy = accuracy_score(ac_y_test[i], predictions[i])
cv_f1.append(f1)
cv_acc.append(accuracy)
scores = [[label_names[l], "f1", f1, "accuracy", accuracy]]
print(scores)
# Export a tree for each label predicted by the clf, not sure if this is needed...
if save_details:
data_fn = "../data/" + data_type + "/rules/weka_rules/" + label_names[
l] + " " + filename + ".txt"
class_names = [label_names[l], "NOT " + label_names[l]]
#self.get_code(clf, cluster_names, class_names, label_names[l] + " " + filename, data_type)
dt.write1dArray(rules[i].split("\n"), data_fn)
dot_file = dt.import1dArray(data_fn)
new_dot_file = []
for line in dot_file:
if "->" not in line and "label" in line and '"t ' not in line and '"f ' not in line:
line = line.split('"')
line[1] = '"' + cluster_names[int(line[1])] + '"'
line = "".join(line)
new_dot_file.append(line)
dt.write1dArray(new_dot_file, data_fn)
graph = pydot.graph_from_dot_file(data_fn)
graph.write_png("../data/" + data_type +
"/rules/weka_images/" + label_names[l] +
" " + filename + ".png")
f1_array.append(np.average(np.asarray(cv_f1)))
accuracy_array.append(np.average(np.asarray(cv_acc)))
accuracy_array = np.asarray(accuracy_array)
accuracy_average = np.average(accuracy_array)
accuracy_array = accuracy_array.tolist()
f1_array = np.asarray(f1_array)
f1_average = np.average(f1_array)
f1_array = f1_array.tolist()
micro_average = f1_score(np.asarray(all_y_test),
np.asarray(all_predictions),
average="micro")
print("Micro F1", micro_average)
accuracy_array.append(accuracy_average)
accuracy_array.append(0.0)
f1_array.append(f1_average)
f1_array.append(micro_average)
scores = [accuracy_array, f1_array]
dt.write1dArray(accuracy_array, acc_fn)
dt.write1dArray(f1_array, f1_fn)
print(csv_fn)
if dt.fileExists(csv_fn):
print("File exists, writing to csv")
try:
dt.write_to_csv(csv_fn, file_names, scores)
except PermissionError:
print("CSV FILE WAS OPEN, WRITING TO ANOTHER FILE")
print("CSV FILE WAS OPEN, WRITING TO ANOTHER FILE")
print("CSV FILE WAS OPEN, WRITING TO ANOTHER FILE")
print("CSV FILE WAS OPEN, WRITING TO ANOTHER FILE")
print("CSV FILE WAS OPEN, WRITING TO ANOTHER FILE")
print("CSV FILE WAS OPEN, WRITING TO ANOTHER FILE")
dt.write_to_csv(
csv_fn[:len(csv_fn) - 4] + str(random.random()) +
"FAIL.csv", file_names, scores)
else:
print("File does not exist, recreating csv")
key = []
for l in label_names:
key.append(l)
key.append("AVERAGE")
key.append("MICRO AVERAGE")
dt.write_csv(csv_fn, file_names, scores, key)
def main(data_type, vector_size, window_size, min_count, sampling_threshold,
negative_size, train_epoch, dm, worker_count, train_wv,
concatenate_wv, use_hierarchical_softmax):
file_name = "Doc2Vec" + " VS" + str(vector_size) + " WS" + str(window_size) + " MC" + str(min_count) + " ST" + str(
sampling_threshold) + \
" NS" + str(negative_size) + " TE" + str(train_epoch) + " DM" + str(dm) + " WC" + str(
worker_count) + "spacy"
" NS" + str(negative_size) + " TE" + str(train_epoch) + " DM" + str(dm) + " WC" + str(worker_count) + \
" TW" + str(train_wv) + " CW" + str(concatenate_wv) + " HS" + str(use_hierarchical_softmax)
corpus_fn = "../data/raw/" + data_type + "/corpus_processed.txt"
if os.path.exists(corpus_fn) is False:
x_train = np.load("../data/raw/" + data_type + "/x_train_w.npy")
x_test = np.load("../data/raw/" + data_type + "/x_test_w.npy")
corpus = np.concatenate((x_train, x_test), axis=0)
text_corpus = np.empty(len(corpus), dtype=np.object)
for i in range(len(corpus)):
text_corpus[i] = " ".join(corpus[i])
print(text_corpus[i])
dt.write1dArray(text_corpus, corpus_fn)
embedding_fn = "/home/tom/Downloads/glove.6B/glove.6B.300d.txt"
model_fn = "../data/" + data_type + "/doc2vec/" + file_name + ".bin"
vector_fn = "../data/" + data_type + "/nnet/spaces/" + file_name + ".npy"
score_fn = "../data/" + data_type + "/doc2vec/" + file_name + "catacc.score"
if os.path.exists(model_fn):
print("Imported model")
model = g.utils.SaveLoad.load(model_fn)
elif file_name[:7] == "Doc2Vec":
model = doc2Vec(embedding_fn, corpus_fn, vector_size, window_size,
min_count, sampling_threshold, negative_size,
train_epoch, dm, worker_count, train_wv,
concatenate_wv, use_hierarchical_softmax)
model.save(model_fn)
if os.path.exists(vector_fn) is False:
vectors = []
for d in range(len(model.docvecs)):
vectors.append(model.docvecs[d])
np.save(vector_fn, vectors)
else:
print("Imported vectors")
vectors = np.load(vector_fn)
if os.path.exists(score_fn) is False or file_name[:6] != "Doc2Vec":
print("Getting score")
if data_type == "sentiment":
classes = dt.import1dArray(
"../data/" + data_type + "/classify/" + data_type +
"/class-all", "i")
x_train, y_train, x_test, y_test = sentiment.getSplits(
vectors, classes)
scores = linearSVMScore(x_train, y_train, x_test, y_test)
else:
classes = dt.import2dArray(
"../data/" + data_type + "/classify/" + data_type +
"/class-all", "i")
x_train, y_train, x_test, y_test = newsgroups.getSplits(
vectors, classes)
scores = multiClassLinearSVM(x_train, y_train, x_test, y_test)
print(scores)
dt.write1dArray(scores, score_fn)
def __init__(self,
vector_path,
class_path,
property_names_fn,
file_name,
svm_type,
training_size=10000,
lowest_count=200,
highest_count=21470000,
get_kappa=True,
get_f1=True,
single_class=True,
data_type="movies",
getting_directions=True,
threads=1,
chunk_amt=0,
chunk_id=0,
rewrite_files=False,
classification="all",
loc="../data/",
logistic_regression=False,
sparse_array_fn=None,
only_these_fn=None):
self.get_kappa = True
self.get_f1 = get_f1
self.data_type = data_type
self.classification = classification
self.lowest_amt = lowest_count
self.higher_amt = highest_count
if chunk_amt > 0:
file_name = file_name + " CID" + str(chunk_id) + " CAMT" + str(
chunk_amt)
directions_fn = loc + data_type + "/svm/directions/" + file_name + ".txt"
ktau_scores_fn = loc + data_type + "/svm/f1/" + file_name + ".txt"
kappa_fn = loc + data_type + "/svm/kappa/" + file_name + ".txt"
acc_fn = loc + data_type + "/svm/acc/" + file_name + ".txt"
TP_fn = loc + data_type + "/svm/stats/TP " + file_name + ".txt"
FP_fn = loc + data_type + "/svm/stats/FP " + file_name + ".txt"
TN_fn = loc + data_type + "/svm/stats/TN " + file_name + ".txt"
FN_fn = loc + data_type + "/svm/stats/FN " + file_name + ".txt"
all_fns = [directions_fn, kappa_fn]
if dt.allFnsAlreadyExist(all_fns) and not rewrite_files:
print("Skipping task", "getSVMResults")
return
else:
print("Running task", "getSVMResults")
y_train = 0
y_test = 0
vectors = np.asarray(dt.import2dArray(vector_path))
print("imported vectors")
if not getting_directions:
classes = np.asarray(dt.import2dArray(class_path))
print("imported classes")
property_names = dt.import1dArray(property_names_fn)
print("imported propery names")
if chunk_amt > 0:
if chunk_id == chunk_amt - 1:
chunk = int(len(property_names) / chunk_amt)
multiply = chunk_amt - 1
property_names = property_names[chunk * multiply:]
else:
property_names = dt.chunks(
property_names, int(
(len(property_names) / chunk_amt)))[chunk_id]
if sparse_array_fn is not None:
sparse_array = dt.import2dArray(sparse_array_fn)
else:
sparse_array = None
if sparse_array is not None:
for s in range(len(sparse_array)):
if len(np.nonzero(sparse_array[s])[0]) <= 1:
print("WILL FAIL", s, len(np.nonzero(sparse_array[s])[0]))
else:
print(len(np.nonzero(sparse_array[s])[0]))
if not getting_directions:
x_train, x_test, y_train, y_test = train_test_split(vectors,
classes,
test_size=0.3,
random_state=0)
else:
x_train = vectors
x_test = vectors
if get_f1:
y_train = y_train.transpose()
y_test = y_test.transpose()
print("transpoosed")
self.x_train = x_train
self.x_test = x_test
self.y_train = y_train
self.y_test = y_test
if only_these_fn is not None:
only_these = dt.import1dArray(only_these_fn, "s")
inds = []
for s in range(len(property_names)):
for o in only_these:
if property_names[s] == o:
inds.append(s)
break
sparse_array = sparse_array[inds]
property_names = property_names[inds]
if self.get_f1 is False:
print("running svms")
kappa_scores, directions, f1_scores, property_names, accs, TPs, FPs, TNs, FNs = self.runAllSVMs(
y_test, y_train, property_names, file_name, svm_type,
getting_directions, threads, logistic_regression, sparse_array)
dt.write1dArray(kappa_scores, kappa_fn)
dt.write2dArray(directions, directions_fn)
dt.write1dArray(f1_scores, ktau_scores_fn)
dt.write1dArray(accs, acc_fn)
dt.write1dArray(TPs, TP_fn)
dt.write1dArray(FPs, FP_fn)
dt.write1dArray(TNs, TN_fn)
dt.write1dArray(FNs, FN_fn)
dt.write1dArray(property_names,
property_names_fn + file_name + ".txt")
else:
final_f1 = []
final_acc = []
for y in range(len(y_train)):
f1, acc = self.runClassifySVM(y_test[y], y_train[y])
print(f1, acc)
final_f1.append(f1)
final_acc.append(acc)
dt.write1dArray(final_f1, ktau_scores_fn)
dt.write1dArray(final_acc, acc_fn)
def __init__(self,
class_path=None,
get_scores=False,
randomize_finetune_weights=False,
dropout_noise=None,
amount_of_hidden=0,
epochs=1,
learn_rate=0.01,
loss="mse",
batch_size=1,
past_model_bias_fn=None,
identity_swap=False,
reg=0.0,
amount_of_finetune=[],
output_size=25,
hidden_activation="tanh",
layer_init="glorot_uniform",
output_activation="tanh",
deep_size=None,
corrupt_finetune_weights=False,
split_to_use=-1,
hidden_layer_size=100,
file_name="unspecified_filename",
vector_path=None,
is_identity=False,
finetune_size=0,
data_type="movies",
optimizer_name="rmsprop",
noise=0.0,
fine_tune_weights_fn=None,
past_model_weights_fn=None,
from_ae=True,
save_outputs=False,
label_names_fn="",
rewrite_files=False,
cv_splits=1,
cutoff_start=0.2,
development=False,
class_weight=None,
csv_fn=None,
tune_vals=False,
get_nnet_vectors_path=None,
classification_name="all",
limit_entities=False,
limited_label_fn="",
vector_names_fn="",
identity_activation="linear",
loc="../data/",
lock_weights_and_redo=False):
weights_fn = loc + data_type + "/nnet/weights/" + file_name + "L0.txt"
bias_fn = loc + data_type + "/nnet/bias/" + file_name + "L0.txt"
rank_fn = loc + data_type + "/nnet/clusters/" + file_name + ".txt"
all_fns = [weights_fn, bias_fn, rank_fn]
if dt.allFnsAlreadyExist(all_fns) and not rewrite_files:
print("Skipping task", "nnet")
return
else:
print("Running task", "nnet")
self.class_path = class_path
self.learn_rate = learn_rate
self.epochs = epochs
self.loss = loss
self.batch_size = batch_size
self.hidden_activation = hidden_activation
self.layer_init = layer_init
self.output_activation = output_activation
self.hidden_layer_size = hidden_layer_size
self.file_name = file_name
self.vector_path = vector_path
self.dropout_noise = dropout_noise
self.finetune_size = finetune_size
self.get_scores = get_scores
self.reg = reg
self.amount_of_finetune = amount_of_finetune
self.amount_of_hidden = amount_of_hidden
self.output_size = output_size
self.identity_swap = identity_swap
self.deep_size = deep_size
self.from_ae = from_ae
self.is_identity = is_identity
self.randomize_finetune_weights = randomize_finetune_weights
self.corrupt_finetune_weights = corrupt_finetune_weights
self.deep_size = deep_size
self.fine_tune_weights_fn = fine_tune_weights_fn
self.identity_activation = identity_activation
self.lock_weights_and_redo = lock_weights_and_redo
print(data_type)
if optimizer_name == "adagrad":
self.optimizer = Adagrad()
elif optimizer_name == "sgd":
self.optimizer = SGD()
elif optimizer_name == "rmsprop":
self.optimizer = RMSprop()
elif optimizer_name == "adam":
self.optimizer = Adam()
elif optimizer_name == "adadelta":
self.optimizer = Adadelta()
else:
print("optimizer not found")
exit()
entity_vectors = np.asarray(dt.import2dArray(self.vector_path))
print("Imported vectors", len(entity_vectors), len(entity_vectors[0]))
if get_nnet_vectors_path is not None:
nnet_vectors = np.asarray(dt.import2dArray(get_nnet_vectors_path))
print("Imported vectors", len(entity_vectors),
len(entity_vectors[0]))
entity_classes = np.asarray(dt.import2dArray(self.class_path))
print("Imported classes", len(entity_classes), len(entity_classes[0]))
if fine_tune_weights_fn is None:
vector_names = dt.import1dArray(vector_names_fn)
limited_labels = dt.import1dArray(limited_label_fn)
entity_vectors = np.asarray(
dt.match_entities(entity_vectors, limited_labels,
vector_names))
if fine_tune_weights_fn is not None:
if len(entity_vectors) != len(entity_classes):
entity_classes = entity_classes.transpose()
print("Transposed classes, now in form", len(entity_classes),
len(entity_classes[0]))
"""
# IF Bow
if len(entity_vectors[0]) != len(entity_classes[0]):
entity_vectors = entity_vectors.transpose()
print("Transposed vectors, now in form", len(entity_vectors), len(entity_vectors[0]))
"""
elif len(entity_vectors) != len(entity_classes):
entity_vectors = entity_vectors.transpose()
print("Transposed vectors, now in form", len(entity_vectors),
len(entity_vectors[0]))
self.input_size = len(entity_vectors[0])
self.output_size = len(entity_classes[0])
if fine_tune_weights_fn is not None:
model_builder = self.fineTuneNetwork
weights = []
if from_ae:
self.past_weights = []
past_model_weights = []
for p in past_model_weights_fn:
past_model_weights.append(
np.asarray(dt.import2dArray(p), dtype="float64"))
past_model_bias = []
for p in past_model_bias_fn:
past_model_bias.append(
np.asarray(dt.import1dArray(p, "f"), dtype="float64"))
for p in range(len(past_model_weights)):
past_model_weights[p] = np.around(past_model_weights[p],
decimals=6)
past_model_bias[p] = np.around(past_model_bias[p],
decimals=6)
for p in range(len(past_model_weights)):
self.past_weights.append([])
self.past_weights[p].append(past_model_weights[p])
self.past_weights[p].append(past_model_bias[p])
for f in fine_tune_weights_fn:
weights.extend(dt.import2dArray(f))
r = np.asarray(weights, dtype="float64")
r = np.asarray(weights, dtype="float64")
for a in range(len(r)):
r[a] = np.around(r[a], decimals=6)
for a in range(len(entity_classes)):
entity_classes[a] = np.around(entity_classes[a], decimals=6)
self.fine_tune_weights = []
self.fine_tune_weights.append(r.transpose())
self.fine_tune_weights.append(
np.zeros(shape=len(r), dtype="float64"))
else:
model_builder = self.classifierNetwork
# Converting labels to categorical
f1_scores = []
accuracy_scores = []
f1_averages = []
accuracy_averages = []
original_fn = file_name
x_train, y_train, x_test, y_test, x_dev, y_dev = split_data.splitData(
vectors, labels[l], data_type)
if development:
x_test = x_dev
y_test = y_dev
model = model_builder()
if get_scores:
test_pred = model.predict(x_train).transpose()
print(test_pred)
highest_vals = [0.5] * len(test_pred) # Default 0.5
y_pred = model.predict(x_test).transpose()
y_test = np.asarray(y_test).transpose()
for y in range(len(y_pred)):
y_pred[y][y_pred[y] >= highest_vals[y]] = 1
y_pred[y][y_pred[y] < highest_vals[y]] = 0
f1_array = []
accuracy_array = []
for y in range(len(y_pred)):
accuracy_array.append(accuracy_score(y_test[y], y_pred[y]))
f1_array.append(
f1_score(y_test[y], y_pred[y], average="binary"))
print(f1_array[y])
y_pred = y_pred.transpose()
y_test = np.asarray(y_test).transpose()
micro_average = f1_score(y_test, y_pred, average="micro")
cv_f1_fn = loc + data_type + "/nnet/scores/F1 " + file_name + ".txt"
cv_acc_fn = loc + data_type + "/nnet/scores/ACC " + file_name + ".txt"
dt.write1dArray(f1_array, cv_f1_fn)
dt.write1dArray(accuracy_array, cv_acc_fn)
f1_scores.append(f1_array)
accuracy_scores.append(accuracy_array)
f1_average = np.average(f1_array)
accuracy_average = np.average(accuracy_array)
f1_averages.append(f1_average)
accuracy_averages.append(accuracy_average)
print("Average F1 Binary", f1_average, "Acc", accuracy_average)
print("Micro Average F1", micro_average)
f1_array.append(f1_average)
f1_array.append(micro_average)
accuracy_array.append(accuracy_average)
accuracy_array.append(0.0)
scores = [accuracy_array, f1_array]
csv_fn = loc + data_type + "/nnet/csv/" + csv_fn + ".csv"
file_names = [file_name + "ACC", file_name + "F1"]
label_names = dt.import1dArray(label_names_fn)
if dt.fileExists(csv_fn):
print("File exists, writing to csv")
try:
dt.write_to_csv(csv_fn, file_names, scores)
except PermissionError:
print("CSV FILE WAS OPEN, WRITING TO ANOTHER FILE")
dt.write_to_csv(
csv_fn[:len(csv_fn) - 4] + str(random.random()) +
"FAIL.csv", [file_name], scores)
else:
print("File does not exist, recreating csv")
key = []
for l in label_names:
key.append(l)
key.append("AVERAGE")
key.append("MICRO AVERAGE")
dt.write_csv(csv_fn, file_names, scores, key)
if save_outputs:
if limit_entities is False:
self.output_clusters = model.predict(nnet_vectors)
else:
self.output_clusters = model.predict(entity_vectors)
self.output_clusters = self.output_clusters.transpose()
dt.write2dArray(self.output_clusters, rank_fn)
for l in range(0, len(model.layers) - 1):
if dropout_noise is not None and dropout_noise > 0.0:
if l % 2 == 1:
continue
print("Writing", l, "layer")
truncated_model = Sequential()
for a in range(l + 1):
truncated_model.add(model.layers[a])
truncated_model.compile(loss=self.loss, optimizer="sgd")
if get_nnet_vectors_path is not None:
self.end_space = truncated_model.predict(nnet_vectors)
else:
self.end_space = truncated_model.predict(entity_vectors)
total_file_name = loc + data_type + "/nnet/spaces/" + file_name
dt.write2dArray(self.end_space,
total_file_name + "L" + str(l) + ".txt")
for l in range(len(model.layers)):
try:
dt.write2dArray(
model.layers[l].get_weights()[0], loc + data_type +
"/nnet/weights/" + file_name + "L" + str(l) + ".txt")
dt.write1dArray(
model.layers[l].get_weights()[1], loc + data_type +
"/nnet/bias/" + file_name + "L" + str(l) + ".txt")
except IndexError:
print("Layer ", str(l), "Failed")
def nameClustersRemoveOutliersWeightDistance(cluster_directions):
# Import the word vectors from Wikipedia
file = open("../data/wikipedia/word_vectors/glove.6B.50d.txt",
encoding="utf8")
weights = dt.import1dArray(weights_fn)
weights = [float(w) for w in weights]
phrases = dt.import1dArray("../data/movies/bow/names/200.txt")
lines = file.readlines()
wv = []
wvn = []
# Create an array of word vectors from the text file
for l in lines:
l = l.split()
wvn.append(l[0])
del l[0]
for i in range(len(l)):
l[i] = float(l[i])
wv.append(l)
words = []
for key, value in cluster_directions.items():
for v in range(len(value) - 1, -1, -1):
if key == value[v] or key == value[v][:-1] or key[:-1] == value[v]:
print("deleted", value[v], key)
value[v] = "DELETE"
for val in reversed(value):
if val == value[v][:-1] or val[:-1] == value[v]:
print("deleted", value[v], val)
value[v] = "DELETE"
for key, value in cluster_directions.items():
for v in range(len(value) - 1, -1, -1):
if value[v] == "DELETE":
del value[v]
# For every cluster (key: cluster center, value: similar terms)
for key, value in cluster_directions.items():
# If the center/values in the vector have a corresponding word vector, add the vectors to an array
cluster_word_vectors = []
cluster_word_vector_names = []
for w in range(len(wvn)):
if wvn[w].strip() == key.strip():
cluster_word_vectors.append(wv[w])
cluster_word_vector_names.append(wvn[w])
print("Success", key)
break
if w == len(wvn) - 1:
print("Failed", key)
for v in range(len(value)):
for w in range(len(wvn)):
if v > 9:
break
if wvn[w].strip() == value[v].strip():
cluster_word_vectors.append(wv[w])
cluster_word_vector_names.append(wvn[w])
print("Success", value[v])
break
if w == len(wvn) - 1:
print("Failed", value[v])
# If we found word vectors
if len(cluster_word_vectors) > 1:
# Get the angular distance between every word vector, and find the minimum angular distance point
min_ang_dist = 214700000
min_index = None
ang_dists = np.zeros(
[len(cluster_word_vectors),
len(cluster_word_vectors)])
for i in range(len(cluster_word_vectors)):
total_dist = 0
for j in range(len(cluster_word_vectors)):
dist = spatial.distance.cosine(cluster_word_vectors[i],
cluster_word_vectors[j])
if ang_dists[i][j] == 0:
ang_dists[i][j] = dist
total_dist += dist
if total_dist < min_ang_dist:
min_ang_dist = total_dist
min_index = i
print("New min word:",
cluster_word_vector_names[min_index])
medoid_wv = []
medoid_wvn = []
dists = []
# Delete outliers
for i in range(len(cluster_word_vectors)):
threshold = 0.8
dist = spatial.distance.cosine(cluster_word_vectors[min_index],
cluster_word_vectors[i])
dists.append(dist)
if dist < threshold:
medoid_wv.append(cluster_word_vectors[i])
medoid_wvn.append(cluster_word_vector_names[i])
else:
print("Deleted outlier", cluster_word_vector_names[i])
if len(medoid_wv) > 1:
for m in range(len(medoid_wv)):
for v in range(len(medoid_wv[m])):
medoid_wv[m][v] = medoid_wv[m][v] * dists[m]
# Get the mean direction of non-outlier directions
mean_vector = dt.mean_of_array(medoid_wv)
# Find the most similar vector to that mean
h_sim = 0
closest_word = ""
for v in range(len(wv)):
sim = st.getSimilarity(wv[v], mean_vector)
if sim > h_sim:
print("New highest sim", wvn[v])
h_sim = sim
closest_word = wvn[v]
print("Closest Word", closest_word)
words.append(closest_word)
else:
words.append(medoid_wvn[0])
else:
words.append(key)
return words
def __init__(self,
features_fn,
classes_fn,
class_names_fn,
cluster_names_fn,
filename,
training_data,
max_depth=None,
balance=None,
criterion="entropy",
save_details=False,
data_type="movies",
cv_splits=5,
csv_fn="../data/temp/no_csv_provided.csv",
rewrite_files=False,
split_to_use=-1,
development=False,
limit_entities=False,
limited_label_fn=None,
vector_names_fn=None,
clusters_fn="",
cluster_duplicates=False,
save_results_so_far=False,
multi_label=False):
label_names = dt.import1dArray(class_names_fn)
filename = filename + str(max_depth)
all_fns = []
file_names = ['ACC ' + filename, 'F1 ' + filename]
acc_fn = '../data/' + data_type + '/rules/tree_scores/' + file_names[
0] + '.scores'
prediction_fn = '../data/' + data_type + '/rules/tree_output/' + filename + '.scores'
f1_fn = '../data/' + data_type + '/rules/tree_scores/' + file_names[
1] + '.scores'
all_top_names_fn = "../data/" + data_type + "/rules/names/" + filename + ".txt"
all_top_rankings_fn = "../data/" + data_type + "/rules/rankings/" + filename + ".txt"
all_top_clusters_fn = "../data/" + data_type + "/rules/clusters/" + filename + ".txt"
fns_name = "../data/" + data_type + "/rules/names/" + filename + label_names[
0] + ".txt"
features_name = "../data/" + data_type + "/rules/rankings/" + filename + label_names[
0] + ".txt"
dt_clusters_name = "../data/" + data_type + "/rules/clusters/" + filename + label_names[
0] + ".txt"
if save_details is False:
all_fns = [acc_fn, f1_fn, prediction_fn, csv_fn]
else:
new_graph_png_fn = '../data/' + data_type + '/rules/tree_images/' + label_names[
0] + " " + filename + '.png'
all_fns = [acc_fn, f1_fn, prediction_fn, csv_fn]
if max_depth is not None:
all_fns.append(all_top_names_fn)
all_fns.append(all_top_rankings_fn)
all_fns.append(all_top_clusters_fn)
if save_details:
orig_dot_file_fn = '../data/' + data_type + '/rules/tree_data/' + label_names[
0] + " " + filename + 'orig.txt'
# all_fns.append(orig_dot_file_fn)
model_name_fn = "../data/" + data_type + "/rules/tree_model/" + label_names[
0] + " " + filename + ".model"
#all_fns.append(model_name_fn)
if dt.allFnsAlreadyExist(all_fns) and not rewrite_files:
print("Skipping task", "DecisionTree")
return
else:
print("Running task", "DecisionTree")
vectors = np.asarray(dt.import2dArray(features_fn))
if data_type == "sentiment": # If it's just a binary class...
labels = np.asarray(dt.import1dArray(classes_fn, "i"))
else:
labels = np.asarray(dt.import2dArray(classes_fn, "i"))
print("vectors", len(vectors), len(vectors[0]))
print("labels", len(labels), len(labels[0]))
if data_type == "sentiment" or len(vectors) != len(labels[0]):
vectors = vectors.transpose()
print("vectors", len(vectors), len(vectors[0]))
cluster_names = dt.import2dArray(cluster_names_fn, "s")
clusters = dt.import2dArray(clusters_fn, "f")
original_vectors = vectors
if "ratings" in classes_fn:
orig_path = "/".join(classes_fn.split("/")[:-1]) + "/"
match_ids_fn = orig_path + "matched_ids.txt"
if os.path.exists(match_ids_fn):
matched_ids = dt.import1dArray(match_ids_fn, "i")
else:
vector_names = dt.import1dArray(vector_names_fn)
limited_labels = dt.import1dArray(limited_label_fn)
matched_ids = dt.match_entities(vector_names, limited_labels)
dt.write1dArray(matched_ids, match_ids_fn)
vectors = vectors[matched_ids]
print("vectors", len(vectors))
print("Past limit entities")
for l in range(len(label_names)):
if label_names[l][:6] == "class-":
label_names[l] = label_names[l][6:]
f1_array = []
accuracy_array = []
prec_array = []
recall_array = []
if not multi_label and data_type != "sentiment":
labels = labels.transpose()
print("labels transposed")
print("labels", len(labels), len(labels[0]))
else:
labels = [labels]
all_top_clusters = []
all_top_rankings = []
all_top_names = []
all_top_inds = []
all_y_test = []
all_predictions = []
print("At label prediction")
for l in range(len(labels)):
# Select training data with cross validationac_y_test = []
cv_acc = []
cv_prec = []
cv_recall = []
c = 0
# If doing cross-validation
if cv_splits > 1:
ac_x_train, ac_y_train, ac_x_test, ac_y_test, ac_x_dev, ac_y_dev = split_data.crossValData(
cv_splits, vectors, labels[l])
else:
x_train, y_train, x_test, y_test, x_dev, y_dev = split_data.splitData(
vectors, labels[l], data_type)
ac_y_train = [x_train]
ac_x_train = [y_train]
ac_x_test = [x_test]
ac_y_test = [y_test]
ac_y_dev = [x_dev]
ac_x_dev = [y_dev]
if development:
ac_x_test = ac_x_dev
ac_y_test = ac_y_dev
for splits in range(len(ac_y_test)):
model_name_fn = "../data/" + data_type + "/rules/tree_model/" + label_names[
l] + " " + filename + ".model"
"""
if dt.fileExists(model_name_fn) and not rewrite_files:
try:
clf = joblib.load(model_name_fn)
except KeyError:
print(model_name_fn) # If a model is disrupted partway through its processing
else:
"""
clf = tree.DecisionTreeClassifier(max_depth=max_depth,
criterion=criterion,
class_weight=balance)
clf.fit(ac_x_train[splits], ac_y_train[splits])
joblib.dump(clf, model_name_fn)
predictions.append(clf.predict(ac_x_test[splits]))
ac_y_test = list(ac_y_test)
predictions = list(predictions)
for i in range(len(predictions)):
print(scores)
class_names = ["NOT " + label_names[l], label_names[l]]
# Export a tree for each label predicted by the clf
if save_details:
orig_dot_file_fn = '../data/' + data_type + '/rules/tree_data/' + label_names[
l] + " " + filename + 'orig.txt'
new_dot_file_fn = '../data/' + data_type + '/rules/tree_data/' + label_names[
l] + " " + filename + '.txt'
orig_graph_png_fn = '../data/' + data_type + '/rules/tree_images/' + label_names[
l] + " " + filename + 'orig.png'
new_graph_png_fn = '../data/' + data_type + '/rules/tree_images/' + label_names[
l] + " " + filename + '.png'
orig_temp_graph_png_fn = '../data/' + data_type + '/rules/tree_temp/' + label_names[
l] + " " + filename + 'orig.png'
new_temp_graph_png_fn = '../data/' + data_type + '/rules/tree_temp/' + label_names[
l] + " " + filename + '.png'
output_names = []
for c in cluster_names:
line = ""
counter = 0
for i in range(len(c)):
line = line + c[i] + " "
counter += 1
if counter == 8:
break
output_names.append(line)
failed = False
try:
tree.export_graphviz(
clf,
feature_names=output_names,
class_names=class_names,
out_file=orig_dot_file_fn,
max_depth=max_depth,
label='all',
filled=True,
impurity=True,
node_ids=True,
proportion=True,
rounded=True,
)
except FileNotFoundError:
try:
orig_dot_file_fn = "//?/" + orig_dot_file_fn
tree.export_graphviz(clf,
feature_names=output_names,
class_names=class_names,
out_file=orig_dot_file_fn,
max_depth=max_depth,
label='all',
filled=True,
impurity=True,
node_ids=True,
proportion=True,
rounded=True)
except FileNotFoundError:
failed = True
print("doesnt work fam")
if failed == False:
rewrite_dot_file = dt.import1dArray(orig_dot_file_fn)
new_dot_file = []
max = 3
min = -3
"""
for f in original_vectors:
for n in f:
if n > max:
max = n
if n < min:
min = n
"""
print(max)
print(min)
boundary = max - min
boundary = boundary / 5
bound_1 = 0 - boundary * 2
bound_2 = 0 - boundary * 1
bound_3 = 0
bound_4 = 0 + boundary
bound_5 = 0 + boundary * 2
for s in rewrite_dot_file:
if ":" in s:
s = s.split("<=")
no_num = s[0]
num = s[1]
num = num.split()
end = " ".join(num[:-1])
num_split = num[0].split("\\")
num = num_split[0]
end = end[len(num):]
num = float(num)
replacement = ""
if num <= bound_2:
replacement = "VERY LOW"
elif num <= bound_3:
replacement = "VERY LOW - LOW"
elif num <= bound_4:
replacement = "VERY LOW - AVERAGE"
elif num <= bound_5:
replacement = "VERY LOW - HIGH"
elif num >= bound_5:
replacement = "VERY HIGH"
new_string_a = [no_num, replacement, end]
new_string = " ".join(new_string_a)
new_dot_file.append(new_string)
if "]" in new_string:
if '"' not in new_string[len(new_string) -
10:]:
for c in range(len(new_string)):
if new_string[c + 1] == "]":
new_string = new_string[:
c] + '"' + new_string[
c:]
break
else:
new_dot_file.append(s)
"""
new_string = s
if "->" not in s and "digraph" not in s and "node" not in s and "(...)" not in s and "}" not in s:
index = s.index("value")
new_string = s[:index] + '"] ;'
new_dot_file.append(new_string)
"""
#new_dot_file.append(s)
dt.write1dArray(new_dot_file, new_dot_file_fn)
try:
orig_graph = pydot.graph_from_dot_file(
orig_dot_file_fn)
new_graph = pydot.graph_from_dot_file(
new_dot_file_fn)
orig_graph.write_png(orig_graph_png_fn)
new_graph.write_png(new_graph_png_fn)
orig_graph.write_png(orig_temp_graph_png_fn)
new_graph.write_png(new_temp_graph_png_fn)
except FileNotFoundError:
orig_graph_png_fn = "//?/" + orig_graph_png_fn
try:
orig_graph.write_png(orig_graph_png_fn)
new_graph_png_fn = "//?/" + new_graph_png_fn
new_graph.write_png(new_graph_png_fn)
except FileNotFoundError:
print("failed graph")
self.get_code(clf, output_names, class_names,
label_names[l] + " " + filename, data_type)
dt_clusters, features, fns, inds = self.getNodesToDepth(
clf, original_vectors, cluster_names, clusters)
print(filename + label_names[l])
fns_name = "../data/" + data_type + "/rules/names/" + filename + label_names[
l] + ".txt"
features_name = "../data/" + data_type + "/rules/rankings/" + filename + label_names[
l] + ".txt"
dt_clusters_name = "../data/" + data_type + "/rules/clusters/" + filename + label_names[
l] + ".txt"
dt.write2dArray(fns, fns_name)
dt.write2dArray(features, features_name)
dt.write2dArray(dt_clusters, dt_clusters_name)
all_top_rankings.extend(features)
all_top_clusters.extend(dt_clusters)
all_top_names.extend(fns)
all_top_inds.extend(inds)
print("len clusters", len(all_top_clusters))
print("len rankings", len(all_top_rankings))
print("len names", len(all_top_names))
if len(all_top_clusters) != len(all_top_rankings) or len(
all_top_clusters) != len(all_top_names):
print("stop")
accuracy_array = np.asarray(accuracy_array)
accuracy_average = np.average(accuracy_array)
prec_array = np.asarray(prec_array)
average_prec = np.average(prec_array)
recall_array = np.asarray(recall_array)
average_recall = np.average(recall_array)
f1_average = 2 * ((average_prec * average_recall) /
(average_prec + average_recall))
if math.isnan(f1_average):
print("NAN", prec, recall)
f1_average = 0.0
all_y_test = np.asarray(all_y_test)
all_predictions = np.asarray(all_predictions)
micro_average = f1_score(all_y_test, all_predictions, average="micro")
accuracy_array = accuracy_array.tolist()
accuracy_array.append(accuracy_average)
accuracy_array.append(0.0)
f1_array.append(f1_average)
f1_array.append(micro_average)
scores = [accuracy_array, f1_array]
dt.write1dArray(accuracy_array, acc_fn)
dt.write1dArray(f1_array, f1_fn)
dt.write2dArray(all_predictions, prediction_fn)
if dt.fileExists(csv_fn):
print("File exists, writing to csv")
try:
dt.write_to_csv(csv_fn, file_names, scores)
except PermissionError:
print("CSV FILE WAS OPEN, SKIPPING")
except ValueError:
print("File does not exist, recreating csv")
key = []
for l in label_names:
key.append(l)
key.append("AVERAGE")
key.append("MICRO AVERAGE")
dt.write_csv(csv_fn, file_names, scores, key)
else:
print("File does not exist, recreating csv")
key = []
for l in label_names:
key.append(l)
key.append("AVERAGE")
key.append("MICRO AVERAGE")
dt.write_csv(csv_fn, file_names, scores, key)
if max_depth is not None:
all_top_names = np.asarray(all_top_names)
all_top_rankings = np.asarray(all_top_rankings)
all_top_clusters = np.asarray(all_top_clusters)
all_top_inds = np.asarray(all_top_inds)
if cluster_duplicates:
ind_to_keep = np.unique(all_top_inds, return_index=True)[1]
all_top_names = all_top_names[ind_to_keep]
all_top_rankings = all_top_rankings[ind_to_keep]
all_top_clusters = all_top_clusters[ind_to_keep]
dt.write2dArray(all_top_names, all_top_names_fn)
dt.write2dArray(all_top_rankings, all_top_rankings_fn)
dt.write2dArray(all_top_clusters, all_top_clusters_fn)
