Select Page

MHN Group – Object Presence Code

import os
import pandas as pd
import matplotlib.pyplot as plt
from tqdm import tqdm
import ast

# === Load CSV ===
input_path = "maslow_image_level_output_deduplicated.csv"
df = pd.read_csv(input_path)

# === Maslow level mappings ===
level_name_map = {
    "level_1": "physiological_needs",
    "level_2": "safety_needs",
    "level_3": "love_and_belonging",
    "level_4": "esteem_needs",
    "level_5": "self-actualization",
    "level_6": "self-Transcendence"
}
maslow_levels = list(level_name_map.values())

# === Colours for plotting ===
maslow_colors = {
    "physiological_needs": "#e6194B",
    "safety_needs": "#f58231",
    "love_and_belonging": "#ffe119",
    "esteem_needs": "#3cb44b",
    "self-actualization": "#911eb4",
    "self-Transcendence": "#8c564b"
}

# === Define your two groups ===
group_1 = [
    "Connection_images", "Creativity", "Education", "freedom", "happiness",
    "human_instinct", "instinct", "nature", "play", "safety"
]
group_2 = [
    "technology_addiction", "doomscrolling", "social_media_addiction", "conformity",
    "overstimulation", "standardisation", "isolation", "danger", "artifical", "sadness", "disconnection"
]

# === Function to process one group ===
def process_group(group_list, group_label):
    percent_data = []
    for category in tqdm(group_list, desc=f"Processing {group_label}"):
        subset = df[df["category"] == category]
        image_level_weights = []

        for _, row in subset.iterrows():
            image_weights = {}
            total_objects = 0
            for raw_level in level_name_map:
                try:
                    obj_list = ast.literal_eval(row[raw_level]) if pd.notna(row[raw_level]) else []
                    obj_count = len(obj_list)
                except:
                    obj_count = 0
                image_weights[raw_level] = obj_count
                total_objects += obj_count

            if total_objects > 0:
                for raw_level in image_weights:
                    image_weights[raw_level] /= total_objects
                image_level_weights.append(image_weights)

        avg_weights = {friendly: 0 for friendly in maslow_levels}
        for weights in image_level_weights:
            for raw_level, friendly_name in level_name_map.items():
                avg_weights[friendly_name] += weights[raw_level]
        num_images = len(image_level_weights)
        if num_images > 0:
            for k in avg_weights:
                avg_weights[k] = round(100 * avg_weights[k] / num_images, 1)
        avg_weights["category"] = category
        percent_data.append(avg_weights)

    # Create and save percent df
    percent_df = pd.DataFrame(percent_data).set_index("category").sort_index()
    percent_df.to_csv(f"{group_label}_per_image_percent.csv")

    # Global normalisation across each Maslow level
    level_totals = percent_df[maslow_levels].sum()
    normalised_df = percent_df[maslow_levels].div(level_totals) * 100
    normalised_df = normalised_df.round(1)
    normalised_df.to_csv(f"{group_label}_double_normalised.csv")

    # Plot
    ax = normalised_df.plot(
        kind="bar",
        figsize=(14, 7),
        edgecolor="black",
        color=[maslow_colors[lvl] for lvl in maslow_levels]
    )
    plt.title(f"{group_label} Category Distribution per Maslow Level (Double Normalised)")
    plt.xlabel("Category")
    plt.ylabel("Percent of Total for Each Maslow Level")
    plt.xticks(rotation=45, ha="right")
    plt.legend(title="Maslow Level")
    plt.tight_layout()
    plt.savefig(f"{group_label}_maslow_chart.png")
    plt.close()

# === Run both groups ===
process_group(group_1, "group1")
process_group(group_2, "group2")

←→