def get_connector(textContent):
if len(textContent) == 3:
text, tension, has_descr = textContent
else:
text, tension = textContent
# add connector according to available description
if tension == '5.0':
# prepend the connector
text = rand(CLIMAX_CONNECTORS) + text + rand(CLIMAX_FINALISERS)
elif '.' not in text:
text = text + '. '
return (text, tension)
def get_connector(textContent):
if len(textContent) == 3:
text, tension, has_descr = textContent
else:
text, tension = textContent
# add connector according to available description
if tension == '5.0':
# prepend the connector
text = rand(CLIMAX_CONNECTORS) + text + rand(CLIMAX_FINALISERS)
elif '.' not in text:
text = text + '. '
return (text, tension)
def new_centroids(data,centroids,clusters,clusters_id,num_of_iterations,num_of_clusters,iteration_count):
#new_centroid = [[float(0) for _ in range(centroids.shape[1])] for _ in range(num_of_clusters)]
new_centroid = []
for i in range(len(clusters)):
val = np.array(clusters[i])
new_centroid.append((np.sum(val,0))/len(clusters[i]))
new_centroid = np.array(new_centroid)
sums = np.sum(np.array(centroids)-np.array(new_centroid))
d = dict()
if(sums==0 or iteration_count==iterations):
print("Converged")
for x in range(len(clusters_id)):
for y in range(len(clusters_id[x])):
d[clusters_id[x][y]] = x+1
vals = [d[x] for x in sorted(d.keys())]
ground_truth = list(map(int,data[:,1]))
print("Jaccard")
ja = helpers.jaccard(ground_truth,vals)
print(ja)
print("Rand index")
rd = helpers.rand(ground_truth,vals)
print(rd)
unique_predicted = list(set(vals))
new_x = helpers.pca(data[:,2:])
helpers.scatter(new_x[:,0],new_x[:,1],vals,unique_predicted,"K-means Algorithm","iyer.txt")
else:
kmeans(data,new_centroid,iterations,no_cluster,iteration_count)
def get_location_by_tension(tension):
'''
Get location dict by exact tension level
Input: integer tension
Output: list location(s)
'''
locations_on_tension = find_by_attribute(LOCATIONS, "Tension", tension)
return rand(locations_on_tension)
def add_location_description(loc):
'''
Adds a short sentence after location identifier which describes
the location.
Let's hope this gives a more realistic feel to the text!
Input: dict or String location
Output: String sentence
'''
if type(loc) == str:
loc = get_location_by_name(loc)
ambience = loc['Ambience']
amb = rand(ambience)
tension = [float(t) for t in loc['Sentiment']]
# attempt to get an appropriate ambience for the location
while True:
amb = rand(ambience)
if (abs(sum(tension) - sum(sentiment(amb))) < 1):
return add_sentence(loc['Location'], amb, nutsness=NUTSNESS)
def add_location_props(loc):
'''
Returns partial sentence of location props.
Input: dict or String location
Output: String " amongst the X" with X a random prop
'''
if type(loc) == str:
loc = get_location_by_name(loc)
props = loc['Props']
if props == [''] or props == '':
return ''
else:
prop = rand(props)
return ' amongst the {}'.format(pluralize(prop))
def new_centroids(reducedSpace, centroids, clusters, clusters_id,
num_of_iterations, num_clusters, iteration_count):
new_centroid = []
for i in range(len(clusters)):
val = np.array(clusters[i])
new_centroid.append((np.sum(val, 0)) / len(clusters[i]))
new_centroid = np.array(new_centroid)
sums = np.sum(np.array(centroids) - np.array(new_centroid))
# sums = 0
d = dict()
if (sums == 0 or iteration_count == iterations):
print("Converged")
for x in range(len(clusters_id)):
for y in range(len(clusters_id[x])):
d[clusters_id[x][y]] = x + 1
vals = [d[x] for x in sorted(d.keys())]
vals = np.array(vals)
print(vals)
print(set(vals))
# ground_truth = list(map(int,GeneExpressions[:,1]))
print("Jaccard")
ja = helpers.jaccard(Groundtruth, vals)
print(ja)
print("Rand index")
rd = helpers.rand(Groundtruth, vals)
print(rd)
unique_predicted = list(set(vals))
new_x = helpers.pca(GeneExpressions)
helpers.scatter(new_x[:, 0], new_x[:, 1], vals, unique_predicted)
else:
kmeans(reducedSpace, new_centroid, iterations, num_clusters,
iteration_count)
# 2. Declare any specific inputs to the program and call the algorithm
epsilon = float(input("Enter epsilon value: "))
min_pts = float(input("Enter min_pts value: "))
# 3. Perform DBSCAN
model = __dbscan.DBSCAN(X, epsilon, min_pts)
predicted = model.fit()
unique, counts = np.unique(predicted, return_counts=True)
print("Counts by cluster:")
for key, value in zip(unique, counts):
print("{}: {}".format(key, value))
# 4. Find Rand index and Jaccard
rand_score = helpers.rand(y, predicted)
jaccard_score = helpers.jaccard(y, predicted)
unique_predicted = list(set(predicted))
print(predicted)
print(rand_score)
print(jaccard_score)
# print(adjusted_rand_score(y, predicted))
# print(jaccard_similarity_score(y, predicted))
# 5. Visualize using PCA
new_X = X
if X.shape[1] > 2:
new_X = helpers.pca(X)
helpers.scatter(new_X[:, 0], new_X[:, 1], predicted, unique_predicted,
def get_location_at_random():
location = rand(find_by_attribute(LOCATIONS, "Preposition", "in"))
return location
def make_characters(n):
'''Get n characters'''
chars = []
for i in range(n):
chars.append(rand(NOC)['Character'])
return chars
# Testing data
#distMatrix = [[0.00,0.71,5.66,3.61,4.24,3.20],[0.71,0.00,4.95,2.92,3.54,2.50],[5.66,4.95,0.00,2.24,1.41,2.50],[3.61,2.92,2.24,0.00,1.00,0.50],[4.24,3.54,1.41,1.00,0.00,1.12],[3.20,2.50,2.50,0.50,1.12,0.00]]
#rowsnumbers = [[0],[1],[2],[3],[4],[5]]
distMatrix = np.array(distMatrix)
#print(distMatrix)
while (len(distMatrix) >= 2):
if (len(rowsnumbers) == k):
break
distMatrix, rowsnumbers = updateDistMatrix(distMatrix, rowsnumbers)
print(rowsnumbers)
clusterassignments = {}
cluster = 1
for i in rowsnumbers:
for j in i:
clusterassignments[j + 1] = cluster
cluster += 1
sorted(clusterassignments)
sorted(Groundtruth)
predicted = list(clusterassignments.values())
unique_predicted = list(set(predicted))
Ground = list(Groundtruth.values())
print(h.jaccard(Ground, predicted))
print(h.rand(Ground, predicted))
new_X = h.pca(GeneExpressions)
h.scatter(new_X[:, 0], new_X[:, 1], predicted, unique_predicted)
