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()