def __init__(self, discrete_labels_fn, ppmi_fn, phrases_fn, phrases_to_check_fn, fn):
ppmi = dt.importLabels(ppmi_fn)
ppmi = np.asarray(ppmi)
phrases = dt.importString(phrases_fn)
indexes_to_get = []
if phrases_to_check_fn != "":
phrases_to_check = dt.importString(phrases_to_check_fn)
for pc in range(len(phrases_to_check)):
for p in range(len(phrases)):
if phrases_to_check[pc] == phrases[p][6:]:
indexes_to_get.append(p)
ppmi = ppmi.transpose()
print len(ppmi), len(ppmi[0])
counter = 0
with open(discrete_labels_fn) as f:
for line in f:
exists = True
if phrases_to_check_fn != "":
exists = False
for i in indexes_to_get:
if i == counter:
exists = True
break
if exists:
discrete_labels = line.split()
saveGraph(discrete_labels, ppmi[counter], fn + " " + phrases[counter][6:])
print phrases[counter]
counter += 1
def __init__(self, cluster_vectors_fn, cluster_labels_fn, movie_names_fn,
label_names_fn, cluster_names_fn, filename, training_data,
cluster_to_classify, max_depth):
vectors = dt.importVectors(cluster_vectors_fn)
labels = dt.importLabels(cluster_labels_fn)
cluster_names = dt.importString(cluster_names_fn)
vector_names = dt.importString(movie_names_fn)
label_names = dt.importString(label_names_fn)
scores_array = []
for l in range(len(labels[0])):
new_labels = [0] * 15000
for x in range(len(labels)):
new_labels[x] = labels[x][l]
x_train = np.asarray(vectors[:training_data])
x_test = np.asarray(vectors[training_data:])
y_train = np.asarray(new_labels[:training_data])
y_test = np.asarray(new_labels[training_data:])
self.clf = tree.DecisionTreeClassifier(max_depth=max_depth)
self.clf = self.clf.fit(x_train, y_train)
y_pred = self.clf.predict(x_test)
f1 = f1_score(y_test, y_pred, average='binary')
accuracy = accuracy_score(y_test, y_pred)
scores = [[label_names[l], "f1", f1, "accuracy", accuracy]]
print scores[0]
scores_array.append(scores)
class_names = [label_names[l], "NOT " + label_names[l]]
tree.export_graphviz(self.clf,
feature_names=cluster_names,
class_names=class_names,
out_file='Rules/' + label_names[l] +
filename + '.dot',
max_depth=10)
"""
rewrite_dot_file = dt.importString('Rules/'+filename+label_names[l]+'.dot')
new_dot_file = []
for s in rewrite_dot_file:
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)
dt.write1dArray(new_dot_file, 'Rules/Cleaned'+filename+label_names[l]+'.dot')
"""
graph = pydot.graph_from_dot_file('Rules/' + label_names[l] +
filename + '.dot')
graph.write_png('Rules/Images/' + label_names[l] + filename +
".png")
self.get_code(self.clf, cluster_names, class_names,
label_names[l] + filename)
dt.write1dArray(scores_array, 'Rules/Scores/' + filename + '.scores')
def getKNeighbors(vector_path="filmdata/films200.mds/films200.mds", class_path="filmdata/classesGenres/class-All",
n_neighbors=1, algorithm="kd_tree", leaf_size=30,
training_data=10000, name="normal200"):
movie_vectors = np.asarray(dt.importVectors(vector_path))
movie_labels = np.asarray(dt.importLabels(class_path))
x_train, y_train, x_test, y_test = dt.splitData(training_data, movie_vectors, movie_labels)
classifier = neighbors.KNeighborsClassifier(n_neighbors=n_neighbors, algorithm=algorithm, leaf_size=leaf_size)
classifier.fit(x_train, y_train.ravel())
y_pred = classifier.predict(x_test)
f1 = f1_score(y_test, y_pred, average='macro')
accuracy = accuracy_score(y_test, y_pred)
dt.write1dArray([f1, accuracy], "KNNScores/" + name + ".score")
print "F1 " + str(f1), "Accuracy", accuracy
def __init__(self, cluster_vectors_fn, cluster_labels_fn, movie_names_fn, label_names_fn, cluster_names_fn, filename, training_data, cluster_to_classify, max_depth):
vectors = dt.importVectors(cluster_vectors_fn)
labels = dt.importLabels(cluster_labels_fn)
cluster_names = dt.importString(cluster_names_fn)
vector_names = dt.importString(movie_names_fn)
label_names = dt.importString(label_names_fn)
scores_array = []
for l in range(len(labels[0])):
new_labels = [0] * 15000
for x in range(len(labels)):
new_labels[x] = labels[x][l]
x_train = np.asarray(vectors[:training_data])
x_test = np.asarray(vectors[training_data:])
y_train = np.asarray(new_labels[:training_data])
y_test = np.asarray(new_labels[training_data:])
self.clf = tree.DecisionTreeClassifier( max_depth=max_depth)
self.clf = self.clf.fit(x_train, y_train)
y_pred = self.clf.predict(x_test)
f1 = f1_score(y_test, y_pred, average='binary')
accuracy = accuracy_score(y_test, y_pred)
scores = [[label_names[l], "f1", f1, "accuracy", accuracy]]
print scores[0]
scores_array.append(scores)
class_names = [ label_names[l], "NOT "+label_names[l]]
tree.export_graphviz(self.clf, feature_names=cluster_names, class_names=class_names, out_file='Rules/'+label_names[l]+filename+'.dot', max_depth=10)
"""
rewrite_dot_file = dt.importString('Rules/'+filename+label_names[l]+'.dot')
new_dot_file = []
for s in rewrite_dot_file:
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)
dt.write1dArray(new_dot_file, 'Rules/Cleaned'+filename+label_names[l]+'.dot')
"""
graph = pydot.graph_from_dot_file('Rules/'+label_names[l]+filename+'.dot')
graph.write_png('Rules/Images/'+label_names[l]+filename+".png")
self.get_code(self.clf, cluster_names, class_names, label_names[l]+filename)
dt.write1dArray(scores_array, 'Rules/Scores/'+filename+'.scores')
def __init__(self, name_distinction="", class_names=None, vector_path=None, class_path=None, class_by_class=True, input_size=200,
training_data=10000, amount_of_scores=400, low_kappa=0.1, high_kappa=0.5, rankSVM=False, amount_to_cut_at=100, largest_cut=21470000):
print "getting movie data"
movie_vectors = dt.importVectors(vector_path)
movie_labels = dt.importLabels(class_path)
print "getting file names"
file_names = dt.getFns(class_path[:-10])
print len(movie_labels), len(movie_labels[0])
print "getting training and test data"
x_train = np.asarray(movie_vectors[:training_data])
x_test = np.asarray(movie_vectors[training_data:])
movie_labels = zip(*movie_labels)
file_names, movie_labels = self.getSampledData(file_names, movie_labels, amount_to_cut_at, largest_cut)
movie_labels = zip(*movie_labels)
y_train = movie_labels[:training_data]
y_test = movie_labels[training_data:]
y_train = np.asarray(zip(*y_train))
y_test = np.asarray(zip(*y_test))
print len(y_train), len(y_test), training_data
print "getting kappa scores"
kappa_scores, directions = self.runAllSVMs(y_test, y_train, x_train, x_test, file_names)
dt.write1dArray(kappa_scores, "SVMResults/"+name_distinction+".scores")
dt.write1dArray(file_names, "SVMResults/"+name_distinction+".names")
dt.write2dArray(directions, "directions/"+name_distinction+".directions")
def getKNeighbors(vector_path="filmdata/films200.mds/films200.mds",
class_path="filmdata/classesGenres/class-All",
n_neighbors=1,
algorithm="kd_tree",
leaf_size=30,
training_data=10000,
name="normal200"):
movie_vectors = np.asarray(dt.importVectors(vector_path))
movie_labels = np.asarray(dt.importLabels(class_path))
x_train, y_train, x_test, y_test = dt.splitData(training_data,
movie_vectors,
movie_labels)
classifier = neighbors.KNeighborsClassifier(n_neighbors=n_neighbors,
algorithm=algorithm,
leaf_size=leaf_size)
classifier.fit(x_train, y_train.ravel())
y_pred = classifier.predict(x_test)
f1 = f1_score(y_test, y_pred, average='macro')
accuracy = accuracy_score(y_test, y_pred)
dt.write1dArray([f1, accuracy], "KNNScores/" + name + ".score")
print "F1 " + str(f1), "Accuracy", accuracy
def __init__(self, direction_fn, ppmi_fn, phrases_fn, phrases_to_check_fn, fn):
ppmi = dt.importLabels(ppmi_fn)
ppmi = np.asarray(ppmi)
phrases = dt.importString(phrases_fn)
indexes_to_get = []
if phrases_to_check_fn != "":
phrases_to_check = dt.importString(phrases_to_check_fn)
for pc in range(len(phrases_to_check)):
for p in range(len(phrases)):
if phrases_to_check[pc] == phrases[p][6:]:
indexes_to_get.append(p)
indexes_to_get.sort()
ppmi = ppmi.transpose()
print len(ppmi), len(ppmi[0])
scores = []
pvalues = []
scores_kendall = []
pvalues_kendall = []
agini = []
agini1 = []
angini1 = []
angini = []
amap = []
andcg = []
counter = 0
averages = []
with open(direction_fn) as f:
for line in f:
exists = True
if phrases_to_check_fn != "":
exists = False
for i in indexes_to_get:
if i == counter:
exists = True
break
if exists:
total = 0
amt = 0
direction = line.split()
for d in range(len(direction)):
direction[d] = float(direction[d])
new_direction = []
new_ppmi = []
direction_rank = np.argsort(direction)
ppmi_rank = np.argsort(ppmi[counter])
for d in range(len(ppmi[counter])):
if ppmi[counter][d] != 0:
total += ppmi[counter][d]
amt += 1
new_direction.append(direction_rank[d])
new_ppmi.append(ppmi_rank[d])
average = total / amt
min_max_scaler = preprocessing.MinMaxScaler()
normalized_ppmi = min_max_scaler.fit_transform(ppmi[counter])
normalized_dir = min_max_scaler.fit_transform(direction)
ginis = gini(normalized_ppmi, normalized_dir)
ranked_ppmi = dt.sortByArray(new_ppmi, new_direction)
nr_ppmi = min_max_scaler.fit_transform(ranked_ppmi)
ndcgs = ndcg_at_k(nr_ppmi, len(nr_ppmi))
#binarizer = preprocessing.Binarizer()
#binary_ppmi = binarizer.transform(normalized_ppmi)
#normalized_dir = np.ndarray.tolist(normalized_dir)
map = 0#average_precision_score(normalized_ppmi, normalized_dir)
rho, pvalue = spearmanr(new_ppmi, new_direction)
rhok, pvaluek = kendalltau(new_ppmi, new_direction)
scores.append(rho)
pvalues.append(pvalue)
scores_kendall.append(rhok)
pvalues_kendall.append(pvaluek)
andcg.append(ndcgs)
agini.append(ginis)
amap.append(map)
averages.append(average)
print phrases[counter] + ":", map, ginis
counter += 1
dt.write1dArray(scores, "RuleType/s" + fn + ".score")
dt.write1dArray(pvalues, "RuleType/s" + fn + ".pvalue")
dt.write1dArray(scores_kendall, "RuleType/k" + fn + ".score")
dt.write1dArray(pvalues_kendall, "RuleType/k" + fn + ".pvalue")
dt.write1dArray(phrases, "RuleType/" + fn + ".names")
dt.write1dArray(averages, "RuleType/" + fn + ".averages")
dt.write1dArray(agini, "RuleType/gn" + fn + ".score")
dt.write1dArray(andcg, "RuleType/ndcg" + fn + ".score")
dt.write1dArray(amap, "RuleType/map" + fn + ".score")
def __init__(self, direction_fn, ppmi_fn, phrases_fn, phrases_to_check_fn,
fn):
ppmi = dt.importLabels(ppmi_fn)
ppmi = np.asarray(ppmi)
phrases = dt.importString(phrases_fn)
indexes_to_get = []
if phrases_to_check_fn != "":
phrases_to_check = dt.importString(phrases_to_check_fn)
for pc in range(len(phrases_to_check)):
for p in range(len(phrases)):
if phrases_to_check[pc] == phrases[p][6:]:
indexes_to_get.append(p)
ppmi = ppmi.transpose()
print len(ppmi), len(ppmi[0])
scores = []
pvalues = []
scores_kendall = []
pvalues_kendall = []
counter = 0
averages = []
with open(direction_fn) as f:
for line in f:
if indexes_to_get is not []:
for i in indexes_to_get:
if i == counter:
total = 0
amt = 0
direction = line.split()
for d in range(len(direction)):
direction[d] = float(direction[d])
new_direction = []
new_ppmi = []
direction_rank = np.argsort(direction)
ppmi_rank = np.argsort(ppmi[counter])
for d in range(len(ppmi[counter])):
if ppmi[counter][d] != 0:
total += ppmi[counter][d]
amt += 1
new_direction.append(direction_rank[d])
new_ppmi.append(ppmi_rank[d])
average = total / amt
rho, pvalue = spearmanr(new_ppmi, new_direction)
scores.append(rho)
pvalues.append(pvalue)
scores_kendall.append(rhok)
pvalues_kendall.append(pvaluek)
averages.append(average)
print phrases[counter] + ":", rho, pvalue, average
else:
direction = line.split()
for d in range(len(direction)):
direction[d] = float(direction[d])
direction_rank = np.argsort(direction)
ppmi_rank = np.argsort(ppmi[counter])
rho, pvalue = spearmanr(direction_rank, ppmi_rank)
scores.append(rho)
pvalues.append(pvalue)
print phrases[counter] + ":", rho, pvalue
counter += 1
dt.write1dArray(scores, "RuleType/s" + fn + ".score")
dt.write1dArray(pvalues, "RuleType/s" + fn + ".pvalue")
dt.write1dArray(scores_kendall, "RuleType/k" + fn + ".score")
dt.write1dArray(pvalues_kendall, "RuleType/k" + fn + ".pvalue")
dt.write1dArray(phrases, "RuleType/" + fn + ".names")
dt.write1dArray(averages, "RuleType/" + fn + ".averages")
def __init__(self, direction_fn, ppmi_fn, phrases_fn, phrases_to_check_fn,
fn):
ppmi = dt.importLabels(ppmi_fn)
ppmi = np.asarray(ppmi)
phrases = dt.importString(phrases_fn)
indexes_to_get = []
if phrases_to_check_fn != "":
phrases_to_check = dt.importString(phrases_to_check_fn)
for pc in range(len(phrases_to_check)):
for p in range(len(phrases)):
if phrases_to_check[pc] == phrases[p][6:]:
indexes_to_get.append(p)
indexes_to_get.sort()
ppmi = ppmi.transpose()
print len(ppmi), len(ppmi[0])
scores = []
pvalues = []
scores_kendall = []
pvalues_kendall = []
agini = []
agini1 = []
angini1 = []
angini = []
amap = []
andcg = []
counter = 0
averages = []
with open(direction_fn) as f:
for line in f:
exists = True
if phrases_to_check_fn != "":
exists = False
for i in indexes_to_get:
if i == counter:
exists = True
break
if exists:
total = 0
amt = 0
direction = line.split()
for d in range(len(direction)):
direction[d] = float(direction[d])
new_direction = []
new_ppmi = []
direction_rank = np.argsort(direction)
ppmi_rank = np.argsort(ppmi[counter])
for d in range(len(ppmi[counter])):
if ppmi[counter][d] != 0:
total += ppmi[counter][d]
amt += 1
new_direction.append(direction_rank[d])
new_ppmi.append(ppmi_rank[d])
average = total / amt
min_max_scaler = preprocessing.MinMaxScaler()
normalized_ppmi = min_max_scaler.fit_transform(
ppmi[counter])
normalized_dir = min_max_scaler.fit_transform(direction)
ginis = gini(normalized_ppmi, normalized_dir)
ranked_ppmi = dt.sortByArray(new_ppmi, new_direction)
nr_ppmi = min_max_scaler.fit_transform(ranked_ppmi)
ndcgs = ndcg_at_k(nr_ppmi, len(nr_ppmi))
#binarizer = preprocessing.Binarizer()
#binary_ppmi = binarizer.transform(normalized_ppmi)
#normalized_dir = np.ndarray.tolist(normalized_dir)
map = 0 #average_precision_score(normalized_ppmi, normalized_dir)
rho, pvalue = spearmanr(new_ppmi, new_direction)
rhok, pvaluek = kendalltau(new_ppmi, new_direction)
scores.append(rho)
pvalues.append(pvalue)
scores_kendall.append(rhok)
pvalues_kendall.append(pvaluek)
andcg.append(ndcgs)
agini.append(ginis)
amap.append(map)
averages.append(average)
print phrases[counter] + ":", map, ginis
counter += 1
dt.write1dArray(scores, "RuleType/s" + fn + ".score")
dt.write1dArray(pvalues, "RuleType/s" + fn + ".pvalue")
dt.write1dArray(scores_kendall, "RuleType/k" + fn + ".score")
dt.write1dArray(pvalues_kendall, "RuleType/k" + fn + ".pvalue")
dt.write1dArray(phrases, "RuleType/" + fn + ".names")
dt.write1dArray(averages, "RuleType/" + fn + ".averages")
dt.write1dArray(agini, "RuleType/gn" + fn + ".score")
dt.write1dArray(andcg, "RuleType/ndcg" + fn + ".score")
dt.write1dArray(amap, "RuleType/map" + fn + ".score")
def __init__(self, direction_fn, ppmi_fn, phrases_fn, phrases_to_check_fn, fn):
ppmi = dt.importLabels(ppmi_fn)
ppmi = np.asarray(ppmi)
phrases = dt.importString(phrases_fn)
indexes_to_get = []
if phrases_to_check_fn != "":
phrases_to_check = dt.importString(phrases_to_check_fn)
for pc in range(len(phrases_to_check)):
for p in range(len(phrases)):
if phrases_to_check[pc] == phrases[p][6:]:
indexes_to_get.append(p)
ppmi = ppmi.transpose()
print len(ppmi), len(ppmi[0])
scores = []
pvalues = []
scores_kendall = []
pvalues_kendall = []
counter = 0
averages = []
with open(direction_fn) as f:
for line in f:
if indexes_to_get is not []:
for i in indexes_to_get:
if i == counter:
total = 0
amt = 0
direction = line.split()
for d in range(len(direction)):
direction[d] = float(direction[d])
new_direction = []
new_ppmi = []
direction_rank = np.argsort(direction)
ppmi_rank = np.argsort(ppmi[counter])
for d in range(len(ppmi[counter])):
if ppmi[counter][d] != 0:
total += ppmi[counter][d]
amt += 1
new_direction.append(direction_rank[d])
new_ppmi.append(ppmi_rank[d])
average = total / amt
rho, pvalue = spearmanr(new_ppmi, new_direction)
scores.append(rho)
pvalues.append(pvalue)
scores_kendall.append(rhok)
pvalues_kendall.append(pvaluek)
averages.append(average)
print phrases[counter] + ":", rho, pvalue, average
else:
direction = line.split()
for d in range(len(direction)):
direction[d] = float(direction[d])
direction_rank = np.argsort(direction)
ppmi_rank = np.argsort(ppmi[counter])
rho, pvalue = spearmanr(direction_rank, ppmi_rank)
scores.append(rho)
pvalues.append(pvalue)
print phrases[counter] + ":", rho, pvalue
counter += 1
dt.write1dArray(scores, "RuleType/s" + fn + ".score")
dt.write1dArray(pvalues, "RuleType/s" + fn + ".pvalue")
dt.write1dArray(scores_kendall, "RuleType/k" + fn + ".score")
dt.write1dArray(pvalues_kendall, "RuleType/k" + fn + ".pvalue")
dt.write1dArray(phrases, "RuleType/" + fn + ".names")
dt.write1dArray(averages, "RuleType/" + fn + ".averages")
