randogoth/lyagushka
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

fixed Z-Scores

Browse source
This commit is contained in:
randogoth 2024-03-01 18:35:31 +02:00
parent 58eb8a2f40
commit a04dfc45ca
3 changed files with 93 additions and 78 deletions
Download patch file Download diff file Expand all files Collapse all files

24
test.py
View file

@ -24,8 +24,12 @@ def generate_random_data(size=1024, max_value=100):
return random_data
def filter_by_z_score(data, z_score_threshold):
filtered_data = [item for item in data if item['z_score'] is not None and abs(item['z_score']) >= z_score_threshold]
return filtered_data
# load the random test data
dataset = []
# dataset = []
# with open('random_values.txt', 'r') as file:
# for line in file:
# random_data.append(int(line.strip()))
@ -33,8 +37,15 @@ dataset = []
dataset = generate_random_data(1024, 1024)
dataset.sort()
with open('dataset.json', 'w') as r:
r.write(json.dumps(dataset, indent=4))
# calculate the anomalies in the data
analysis_results = json.loads(lyagushka(dataset, 3.0, 7))
analysis_results = json.loads(lyagushka(dataset, 4.0, 7))
analysis_results = filter_by_z_score(analysis_results, 1.0)
with open('result.json', 'w') as r:
r.write(json.dumps(analysis_results, indent=4))
# Initialize plot
plt.figure(figsize=(10, 6))
@ -45,15 +56,12 @@ colors = plt.cm.jet(np.linspace(0, 1, len(analysis_results)))
# Plot dataset points and assign colors based on cluster membership
for i, result in enumerate(analysis_results):
if result['num_elements'] > 0: # It's a cluster
points_in_cluster = [point for point in dataset if
result['centroid'] - result['span_length'] / 2 <= point <=
result['centroid'] + result['span_length'] / 2]
for point in points_in_cluster:
for point in dataset:
plt.plot(point, 0, 'o', color=colors[i]) # Plot points in cluster with the same color
# Plot a line segment for the cluster/gap Z-score in the same color
start = result['centroid'] - result['span_length'] / 2
end = result['centroid'] + result['span_length'] / 2
start = result['start']
end = result['end']
z_score = result['z_score'] if result['z_score'] is not None else 0
plt.plot([start, end], [z_score, z_score], color=colors[i], linewidth=2)