Committee/Secure-OCF-Web-Hosting
Archived
5
0
Fork 0
Code Issues 9 Pull Requests Actions Packages Projects Releases Wiki Activity

Metrics - Version, Downloads, etc. #7

New Issue
Open
opened 2025-10-08 04:47:57 +00:00 by serrindipity · 2 comments
serrindipity commented 2025-10-08 04:47:57 +00:00
Member
Copy Link
Copy Source

Use branch metrics

Use branch `metrics`
douglastsui commented 2025-10-08 04:53:36 +00:00
Copy Link
Copy Source

Descriptive Statistics for downloaded:
Mean: 240046.51333118603
Median: 2757.0
Standard Deviation: 6850631.178687502
Variance: 46931147546405.305
Minimum: 0
Maximum: 862378311
Sum: 13414759351

Percentiles:
25th Percentile: 1248.0
50th Percentile (Median): 2757.0
75th Percentile: 9007.5
90th Percentile: 48709.700000000004

Descriptive Statistics for rating:
Mean: 46.012597523441414
Median: 40.0
Standard Deviation: 46.36869587925876
Variance: 2150.055957543188
Minimum: 0
Maximum: 100
Sum: 2571368

Percentiles:
25th Percentile: 0.0
50th Percentile (Median): 40.0
75th Percentile: 100.0
90th Percentile: 100.0

Descriptive Statistics for active_installs:
Mean: 6089.0397967217805
Median: 20.0
Standard Deviation: 124200.36122887746
Variance: 15425729729.383648
Minimum: 0
Maximum: 10000000
Sum: 340279900

Percentiles:
25th Percentile: 10.0
50th Percentile (Median): 20.0
75th Percentile: 100.0
90th Percentile: 1000.0

Descriptive Statistics for num_ratings:
Mean: 14.758070288454656
Median: 1.0
Standard Deviation: 195.3196365356121
Variance: 38149.76041640362
Minimum: 0
Maximum: 27774
Sum: 824740

Percentiles:
25th Percentile: 0.0
50th Percentile (Median): 1.0
75th Percentile: 3.0
90th Percentile: 12.0

Descriptive Statistics for downloaded: Mean: 240046.51333118603 Median: 2757.0 Standard Deviation: 6850631.178687502 Variance: 46931147546405.305 Minimum: 0 Maximum: 862378311 Sum: 13414759351 Percentiles: 25th Percentile: 1248.0 50th Percentile (Median): 2757.0 75th Percentile: 9007.5 90th Percentile: 48709.700000000004 Descriptive Statistics for rating: Mean: 46.012597523441414 Median: 40.0 Standard Deviation: 46.36869587925876 Variance: 2150.055957543188 Minimum: 0 Maximum: 100 Sum: 2571368 Percentiles: 25th Percentile: 0.0 50th Percentile (Median): 40.0 75th Percentile: 100.0 90th Percentile: 100.0 Descriptive Statistics for active_installs: Mean: 6089.0397967217805 Median: 20.0 Standard Deviation: 124200.36122887746 Variance: 15425729729.383648 Minimum: 0 Maximum: 10000000 Sum: 340279900 Percentiles: 25th Percentile: 10.0 50th Percentile (Median): 20.0 75th Percentile: 100.0 90th Percentile: 1000.0 Descriptive Statistics for num_ratings: Mean: 14.758070288454656 Median: 1.0 Standard Deviation: 195.3196365356121 Variance: 38149.76041640362 Minimum: 0 Maximum: 27774 Sum: 824740 Percentiles: 25th Percentile: 0.0 50th Percentile (Median): 1.0 75th Percentile: 3.0 90th Percentile: 12.0
Screenshot 2025-10-07 215318.png
63 KiB
Screenshot 2025-10-07 215318.png
douglastsui commented 2025-10-08 04:56:04 +00:00
Copy Link
Copy Source
from time import sleep

import requests
import json

from tqdm import tqdm

starting_page = 1
request_per_page = 100
response = requests.get(f"https://api.wordpress.org/plugins/info/1.2/?action=query_plugins"
                        f"&request[page]={starting_page}"
                        f"&request[per_page]={request_per_page}")
response_json = response.json()
# print(response_json)

page_no = response_json['info']['pages']
plugins_info_list = []
plugins_info_str = ""
for i in tqdm(range(page_no)):
    response = requests.get(f"https://api.wordpress.org/plugins/info/1.2/?action=query_plugins"
                            f"&request[page]={i+1}"
                            f"&request[per_page]={request_per_page}")
    response_json = response.json()
    plugins_info_list.append(response_json['plugins'])
    # plugins_info_str += str(response_json['plugins'])
    sleep(0.1)

flattened_list = [item for sublist in plugins_info_list for item in sublist]

plugins_info_json = json.dumps(flattened_list, indent=4)
print(plugins_info_json)

filename = "output.json"

# Open the file in write mode ('w') and use json.dump() to write the data
with open(filename, 'w') as f:
    f.write(plugins_info_json)

import json
import matplotlib.pyplot as plt
import numpy as np

def print_info(name, data):
    # Convert the list to a NumPy array
    data_np = np.array(data)

    # Calculate basic statistics
    mean = np.mean(data_np)
    median = np.median(data_np)
    std_dev = np.std(data_np)
    variance = np.var(data_np)
    min_val = np.min(data_np)
    max_val = np.max(data_np)
    sum_val = np.sum(data_np)

    # Calculate percentiles
    percentile_25 = np.percentile(data_np, 25)
    percentile_50 = np.percentile(data_np, 50)  # This is the same as the median
    percentile_75 = np.percentile(data_np, 75)
    percentile_90 = np.percentile(data_np, 90)

    # Print the results
    print(f"\n\nDescriptive Statistics for {name}:")
    print(f"Mean: {mean}")
    print(f"Median: {median}")
    print(f"Standard Deviation: {std_dev}")
    print(f"Variance: {variance}")
    print(f"Minimum: {min_val}")
    print(f"Maximum: {max_val}")
    print(f"Sum: {sum_val}")
    print("\nPercentiles:")
    print(f"25th Percentile: {percentile_25}")
    print(f"50th Percentile (Median): {percentile_50}")
    print(f"75th Percentile: {percentile_75}")
    print(f"90th Percentile: {percentile_90}")


with open('output.json', 'r') as f:
    json_data = json.load(f)

# print(len(data))
downloaded = [plugin["downloaded"] for plugin in json_data]
rating = [plugin["rating"] for plugin in json_data]
active_installs = [plugin["active_installs"] for plugin in json_data]
num_ratings = [plugin["num_ratings"] for plugin in json_data]

print_info("downloaded", downloaded)
print_info("rating", rating)
print_info("active_installs", active_installs)
print_info("num_ratings", num_ratings)

# plt.hist(downloaded, bins=500, log=True)
# plt.show()
fig, axs = plt.subplots(nrows=2, ncols=2, figsize=(8, 6))
axs[0,0].hist(downloaded, bins=100, log=True)
axs[0,0].set_title("Distribution of downloaded")

axs[0,1].hist(rating, bins=20, log=True)
axs[0,1].set_title("Distribution of rating")

axs[1,0].hist(active_installs, bins=10, log=True)
axs[1,0].set_title("Distribution of active_installs")

axs[1,1].hist(num_ratings, bins=100, log=True)
axs[1,1].set_title("Distribution of num_ratings")

# Add labels and title
# plt.xlabel("Value")
# plt.ylabel("Frequency (log)")

# Display the plot
plt.show()
``` from time import sleep import requests import json from tqdm import tqdm starting_page = 1 request_per_page = 100 response = requests.get(f"https://api.wordpress.org/plugins/info/1.2/?action=query_plugins" f"&request[page]={starting_page}" f"&request[per_page]={request_per_page}") response_json = response.json() # print(response_json) page_no = response_json['info']['pages'] plugins_info_list = [] plugins_info_str = "" for i in tqdm(range(page_no)): response = requests.get(f"https://api.wordpress.org/plugins/info/1.2/?action=query_plugins" f"&request[page]={i+1}" f"&request[per_page]={request_per_page}") response_json = response.json() plugins_info_list.append(response_json['plugins']) # plugins_info_str += str(response_json['plugins']) sleep(0.1) flattened_list = [item for sublist in plugins_info_list for item in sublist] plugins_info_json = json.dumps(flattened_list, indent=4) print(plugins_info_json) filename = "output.json" # Open the file in write mode ('w') and use json.dump() to write the data with open(filename, 'w') as f: f.write(plugins_info_json) ``` ``` import json import matplotlib.pyplot as plt import numpy as np def print_info(name, data): # Convert the list to a NumPy array data_np = np.array(data) # Calculate basic statistics mean = np.mean(data_np) median = np.median(data_np) std_dev = np.std(data_np) variance = np.var(data_np) min_val = np.min(data_np) max_val = np.max(data_np) sum_val = np.sum(data_np) # Calculate percentiles percentile_25 = np.percentile(data_np, 25) percentile_50 = np.percentile(data_np, 50) # This is the same as the median percentile_75 = np.percentile(data_np, 75) percentile_90 = np.percentile(data_np, 90) # Print the results print(f"\n\nDescriptive Statistics for {name}:") print(f"Mean: {mean}") print(f"Median: {median}") print(f"Standard Deviation: {std_dev}") print(f"Variance: {variance}") print(f"Minimum: {min_val}") print(f"Maximum: {max_val}") print(f"Sum: {sum_val}") print("\nPercentiles:") print(f"25th Percentile: {percentile_25}") print(f"50th Percentile (Median): {percentile_50}") print(f"75th Percentile: {percentile_75}") print(f"90th Percentile: {percentile_90}") with open('output.json', 'r') as f: json_data = json.load(f) # print(len(data)) downloaded = [plugin["downloaded"] for plugin in json_data] rating = [plugin["rating"] for plugin in json_data] active_installs = [plugin["active_installs"] for plugin in json_data] num_ratings = [plugin["num_ratings"] for plugin in json_data] print_info("downloaded", downloaded) print_info("rating", rating) print_info("active_installs", active_installs) print_info("num_ratings", num_ratings) # plt.hist(downloaded, bins=500, log=True) # plt.show() fig, axs = plt.subplots(nrows=2, ncols=2, figsize=(8, 6)) axs[0,0].hist(downloaded, bins=100, log=True) axs[0,0].set_title("Distribution of downloaded") axs[0,1].hist(rating, bins=20, log=True) axs[0,1].set_title("Distribution of rating") axs[1,0].hist(active_installs, bins=10, log=True) axs[1,0].set_title("Distribution of active_installs") axs[1,1].hist(num_ratings, bins=100, log=True) axs[1,1].set_title("Distribution of num_ratings") # Add labels and title # plt.xlabel("Value") # plt.ylabel("Frequency (log)") # Display the plot plt.show() ```
devcheezy self-assigned this 2025-10-08 05:21:37 +00:00
douglastsui was assigned by devcheezy 2025-10-08 05:21:55 +00:00
kuljit added reference metrics 2025-10-08 22:28:03 +00:00
This repo is archived. You cannot comment on issues.
metrics
Branches Tags
Labels
No items
No labels
Milestone
No items
No Milestone
Projects
Clear projects
No projects
Assignees
Clear assignees
Dvls (Dvls) Kinn (Kinn) sohcato (sohcato)
No Assignees douglastsui devcheezy
2 Participants
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Committee/Secure-OCF-Web-Hosting#7