feat: initial EDA

import pandas as pd

import numpy as np

import ast

import matplotlib.pyplot as plt

# Load dataset (example CSV)

df = pd.read_csv("./data/games_03_2025_reduced.csv")

# --- 1. Parse JSON/array columns ---

# supported_languages might be a string like "['English', 'French']"

if df['supported_languages'].dtype == object:

    df['supported_languages'] = df['supported_languages'].apply(

        lambda x: ast.literal_eval(x) if pd.notna(x) and x.startswith('[') else []

    )

def parse_tags(x):

    """

    Parses a string representation of a dictionary or an empty list.

    Handles NaN values, dictionary-like strings ("{'tag': count}"),

    and empty list strings ("[]").

    """

    if pd.isna(x) or x == '[]':

        return {}

    try:

        return ast.literal_eval(str(x))

    except (ValueError, SyntaxError):

        return {}

df['tags'] = df['tags'].apply(parse_tags)

# --- 2. Handle price=0 ---

def clean_price(row):

    price = row['price']

    tags = row['tags']

    if price == 0:

        if isinstance(tags, dict) and any(t.lower() == "free to play" for t in tags.keys()):

            return 0  # true free to play

        else:

            return np.nan  # treat as missing

    return price

df['price_clean'] = df.apply(clean_price, axis=1)

# --- 4. Clean playtime columns ---

# 0 playtime might mean missing if no one played / no data

playtime_cols = ['average_playtime_forever', 'median_playtime_forever',

                 'average_playtime_2weeks', 'median_playtime_2weeks']

for col in playtime_cols:

    df[col + "_clean"] = df[col].replace(0, np.nan)

# --- 5. Missingness exploration ---

print("\n--- Dataset size ---")

print(df.shape)

print("\n--- Missing values (NaN only) ---")

print(df.isna().sum().sort_values(ascending=False))

print("\n--- Potential pseudo-missing values (zeros in numeric columns) ---")

num_cols = df.select_dtypes(include=[np.number]).columns

zero_counts = (df[num_cols] == 0).sum().sort_values(ascending=False)

print(zero_counts)

# --- 6. Basic EDA ---

print("\n--- Price overview ---")

print(df['price_clean'].describe())

print("\n--- Playtime overview (hours) ---")

print((df['average_playtime_forever_clean'] / 60).describe())  # convert mins → hours

print("\n--- Reviews overview ---")

print(df[['num_reviews_total', 'pct_pos_total']].describe())

# --- 7. Visualization Examples ---

# Distribution of prices

df['price_clean'].dropna().plot(kind='hist', bins=50, logy=True, title="Price distribution")

plt.xlabel("Price ($)")

plt.show()

# Playtime vs Reviews

plt.scatter(df['average_playtime_forever_clean']/60, df['num_reviews_total'], alpha=0.3)

plt.xscale("log")

plt.yscale("log")

plt.xlabel("Average Playtime (hours, log)")

plt.ylabel("Total Reviews (log)")

plt.title("Playtime vs Reviews")

plt.show()

# --- 8. Language & Tag exploration ---

# Top supported languages

from collections import Counter

lang_counts = Counter([lang for langs in df['supported_languages'] for lang in langs])

print("\n--- Top supported languages ---")

print(pd.Series(lang_counts).sort_values(ascending=False).head(10))

# Top tags

tag_counts = Counter([tag for tags in df['tags'] for tag in tags.keys()])

print("\n--- Top tags ---")

print(pd.Series(tag_counts).sort_values(ascending=False).head(10))