Challenge Solution - Samantha Catonio

.env

@@ -0,0 +1,6 @@
+DB_HOST="35.199.115.174"
+DB_USER="looqbox-challenge"
+DB_PASSWORD="looq-challenge"
+DB_NAME="looqbox-challenge"
+DB_PORT=3306
+

IMDB/IMDB_diretores.py

@@ -0,0 +1,97 @@
+import pandas as pd
+import matplotlib.pyplot as plt
+from matplotlib.colors import LinearSegmentedColormap
+from db_connection import engine
+
+
+def get_movies():
+    query = """
+        SELECT
+            Director,
+            Rating
+        FROM `looqbox-challenge`.IMDB_movies
+        WHERE Director IS NOT NULL;
+    """
+    return pd.read_sql(query, engine)
+
+
+def calculate_top_directors(df, min_movies=3, top_n=15):
+    return (
+        df.groupby("Director")
+        .filter(lambda x: len(x) >= min_movies)
+        .groupby("Director")
+        .agg(
+            Avg_Rating=("Rating", "mean"),
+            Count=("Rating", "count")
+        )
+        .reset_index()
+        .sort_values("Avg_Rating", ascending=False)
+        .head(top_n)
+    )
+
+
+def plot_top_directors(df_directors):
+    looqbox_cmap = LinearSegmentedColormap.from_list(
+        "looqbox", ["#B0B0B0", "#3DBE6E"]
+    )
+
+    df_directors = df_directors.sort_values("Avg_Rating", ascending=True)
+
+    n = len(df_directors)
+    colors = [looqbox_cmap(i / (n - 1)) for i in range(n)]
+
+    fig, ax = plt.subplots(figsize=(11, 7))
+
+    bars = ax.barh(
+        df_directors["Director"],
+        df_directors["Avg_Rating"] - 5,
+        color=colors,
+        edgecolor="white",
+        linewidth=0.5,
+        left=5
+    )
+
+    for bar, rating, count in zip(bars, df_directors["Avg_Rating"], df_directors["Count"]):
+        ax.text(
+            bar.get_x() + bar.get_width() + 0.02,
+            bar.get_y() + bar.get_height() / 2,
+            f"{rating:.2f}  ({count} filmes)",
+            va="center",
+            fontsize=9,
+            color="#444444"
+        )
+
+    avg = df_directors["Avg_Rating"].mean()
+    ax.axvline(
+        avg,
+        color="#e74c3c",
+        linestyle="--",
+        linewidth=1.5,
+        label=f"Group Average: {avg:.2f}"
+    )
+
+    ax.set_xlim(5, df_directors["Avg_Rating"].max() + 0.5)
+    ax.set_title(
+        "Most Consistent Directors by IMDb Rating",
+        fontsize=14, fontweight="bold", pad=15
+    )
+    ax.set_xlabel("Average IMDb Rating", fontsize=11)
+    ax.set_ylabel("Director", fontsize=11)
+    ax.legend(fontsize=10)
+    ax.grid(axis="x", alpha=0.3)
+    ax.spines["top"].set_visible(False)
+    ax.spines["right"].set_visible(False)
+    plt.tight_layout()
+    plt.show()
+
+def main():
+    movies = get_movies()
+    top_directors = calculate_top_directors(movies)
+
+    print(top_directors.to_string(index=False))
+
+    plot_top_directors(top_directors)
+
+
+if __name__ == "__main__":
+    main()

IMDB/IMDB_genero.py

@@ -0,0 +1,101 @@
+import pandas as pd
+import matplotlib.pyplot as plt
+from db_connection import engine
+from matplotlib.colors import LinearSegmentedColormap
+
+def get_movies():
+    query = """
+        SELECT
+            Title,
+            Genre,
+            Rating
+        FROM `looqbox-challenge`.IMDB_movies
+        WHERE Genre IS NOT NULL;
+    """
+    return pd.read_sql(query, engine)
+
+
+def expand_genres(df):
+    df["Genre"] = df["Genre"].str.split(",")
+    df = df.explode("Genre")
+    df["Genre"] = df["Genre"].str.strip()
+    return df
+
+
+def calculate_avg_by_genre(df):
+    return (
+        df.groupby("Genre")
+        .agg(
+            Avg_Rating=("Rating", "mean"),
+            Count=("Title", "count")
+        )
+        .reset_index()
+        .sort_values("Avg_Rating", ascending=False)
+    )
+
+
+def plot_rating_by_genre(df_genre):
+    fig, ax = plt.subplots(figsize=(11, 8))
+
+    looqbox_cmap = LinearSegmentedColormap.from_list(
+        "looqbox", ["#B0B0B0", "#3DBE6E"]
+    )
+
+    n = len(df_genre)
+    colors = [looqbox_cmap(i / (n - 1)) for i in range(n)]
+    colors = colors[::-1] 
+
+    bars = ax.barh(
+        df_genre["Genre"],
+        df_genre["Avg_Rating"] - 5,
+        color=colors,
+        edgecolor="white",
+        linewidth=0.5,
+        left=5
+    )
+
+    for bar, rating, count in zip(bars, df_genre["Avg_Rating"], df_genre["Count"]):
+        ax.text(
+            bar.get_x() + bar.get_width() + 0.02,
+            bar.get_y() + bar.get_height() / 2,
+            f"{rating:.2f}  ({count} filmes)",
+            va="center",
+            fontsize=9,
+            color="#444444"
+        )
+
+    avg = df_genre["Avg_Rating"].mean()
+    ax.axvline(
+        avg,
+        color="#e74c3c",
+        linestyle="--",
+        linewidth=1.5,
+        label=f"Overall Average: {avg:.2f}"
+    )
+
+    ax.set_xlim(5, df_genre["Avg_Rating"].max() + 0.5)
+    ax.set_title("Average IMDb Rating by Genre", fontsize=14, fontweight="bold", pad=15)
+    ax.set_xlabel("Average Rating", fontsize=11)
+    ax.set_ylabel("Genre", fontsize=11)
+    ax.legend(fontsize=10)
+    ax.invert_yaxis()
+    ax.grid(axis="x", alpha=0.3)
+    ax.spines["top"].set_visible(False)
+    ax.spines["right"].set_visible(False)
+    plt.tight_layout()
+    plt.show()
+
+
+def main():
+    movies = get_movies()
+    movies = expand_genres(movies)
+
+    avg_by_genre = calculate_avg_by_genre(movies)
+
+    print(avg_by_genre.to_string(index=False))
+
+    plot_rating_by_genre(avg_by_genre)
+
+
+if __name__ == "__main__":
+    main()

IMDB/IMDB_metascore.py

@@ -0,0 +1,108 @@
+import pandas as pd
+import matplotlib.pyplot as plt
+from matplotlib.colors import LinearSegmentedColormap
+from db_connection import engine
+
+
+def get_movies():
+    query = """
+        SELECT
+            Title,
+            Rating,
+            Metascore,
+            Genre
+        FROM `looqbox-challenge`.IMDB_movies
+        WHERE Metascore IS NOT NULL;
+    """
+    return pd.read_sql(query, engine)
+
+
+def calculate_difference(df):
+    df["Rating_scaled"] = df["Rating"] * 10
+    df["Difference"] = df["Rating_scaled"] - df["Metascore"]
+    return df
+
+
+def get_looqbox_cmap():
+    return LinearSegmentedColormap.from_list(
+        "looqbox", ["#B0B0B0", "#3DBE6E"]
+    )
+
+
+def plot_divergence(df):
+    top = (
+        df.reindex(df["Difference"].abs().sort_values(ascending=False).index)
+        .head(20)
+        .sort_values("Difference")
+    )
+
+    cmap = get_looqbox_cmap()
+    norm = (top["Difference"] - top["Difference"].min()) / (
+        top["Difference"].max() - top["Difference"].min()
+    )
+    colors = [cmap(v) for v in norm]
+
+    fig, ax = plt.subplots(figsize=(11, 8))
+
+    bars = ax.barh(
+        top["Title"],
+        top["Difference"],
+        color=colors,
+        edgecolor="white",
+        linewidth=0.5
+    )
+
+    for bar, val in zip(bars, top["Difference"]):
+        x = bar.get_width()
+        ax.text(
+            x + (0.5 if x >= 0 else -0.5),
+            bar.get_y() + bar.get_height() / 2,
+            f"{val:+.1f}",
+            va="center",
+            ha="left" if x >= 0 else "right",
+            fontsize=9,
+            color="#444444"
+        )
+
+    ax.axvline(0, color="#444444", linewidth=1)
+
+    ax.text(
+        top["Difference"].max() * 0.3, -2,
+        "► Público gostou mais",
+        color="#3DBE6E", fontsize=10, fontweight="bold"
+    )
+    ax.text(
+        top["Difference"].min() * 0.9, -2,
+        "◄ Crítica gostou mais",
+        color="#B0B0B0", fontsize=10, fontweight="bold"
+    )
+
+    ax.set_title(
+        "Audience vs Critics: Who Liked It More?",
+        fontsize=14, fontweight="bold", pad=15
+    )
+    ax.set_xlabel("Difference (Audience Score - Critics Score)", fontsize=11)
+    ax.grid(axis="x", alpha=0.3)
+    ax.spines["top"].set_visible(False)
+    ax.spines["right"].set_visible(False)
+    plt.tight_layout()
+    plt.show()
+
+
+def main():
+    movies = get_movies()
+    movies = calculate_difference(movies)
+
+    print("Top 10 Biggest Disagreements:\n")
+    print(
+        movies.reindex(movies["Difference"].abs().sort_values(ascending=False).index)
+        [["Title", "Rating", "Metascore", "Difference"]]
+        .head(10)
+        .to_string(index=False)
+    )
+
+    plot_divergence(movies)
+
+
+if __name__ == "__main__":
+    main()