Skip to content

Visualization Module

Visualizer

Source code in src/visualize.py 
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
class Visualizer:
    @staticmethod
    def plot_genre_distribution(movies: pd.DataFrame):
        """Plot distribution of movie genres"""
        # Get all unique genres
        all_genres = set()
        for genres_list in movies["genres"]:
            if isinstance(genres_list, list):
                all_genres.update(genres_list)

        # Count genre occurrences
        genre_counts = {}
        for genre in all_genres:
            if genre != "(no genres listed)":
                genre_counts[genre] = movies[genre].sum()

        # Plot
        plt.figure(figsize=(12, 8))
        genres = list(genre_counts.keys())
        counts = list(genre_counts.values())

        plt.barh(genres, counts)
        plt.title("Movie Genre Distribution")
        plt.xlabel("Number of Movies")
        plt.tight_layout()
        plt.savefig(
            f"{vis_dir}/genre_distribution.png", dpi=300, bbox_inches="tight"
        )
        plt.show()

    @staticmethod
    def plot_rating_distribution(ratings: pd.DataFrame):
        """Plot distribution of ratings"""
        plt.figure(figsize=(10, 6))
        sns.histplot(ratings["rating"], bins=10, kde=True)
        plt.title("Rating Distribution")
        plt.xlabel("Rating")
        plt.ylabel("Frequency")
        plt.tight_layout()
        plt.savefig(
            f"{vis_dir}/rating_distribution.png", dpi=300, bbox_inches="tight"
        )
        plt.show()

    @staticmethod
    def plot_movies_per_year(movies: pd.DataFrame):
        """Plot number of movies released per year"""
        # Extract year from title (assuming format like "Movie Title (Year)")
        movies["year"] = movies["title"].str.extract(r"\((\d{4})\)")
        movies["year"] = pd.to_numeric(movies["year"], errors="coerce")

        # Filter valid years
        movies_with_year = movies.dropna(subset=["year"])
        movies_with_year = movies_with_year[movies_with_year["year"] >= 1900]

        plt.figure(figsize=(12, 6))
        year_counts = movies_with_year["year"].value_counts().sort_index()
        plt.plot(year_counts.index, year_counts.values, linewidth=2)
        plt.title("Number of Movies Released Per Year")
        plt.xlabel("Year")
        plt.ylabel("Number of Movies")
        plt.grid(True, alpha=0.3)
        plt.tight_layout()
        plt.savefig(
            f"{vis_dir}/movies_per_year.png", dpi=300, bbox_inches="tight"
        )
        plt.show()

    @staticmethod
    def plot_top_rated_movies(df: pd.DataFrame, min_ratings=50):
        """Plot top rated movies with minimum number of ratings"""
        # Calculate average rating and count for each movie
        movie_stats = (
            df.groupby("title")
            .agg({"rating": ["mean", "count"]})
            .reset_index()
        )

        # Flatten column names
        movie_stats.columns = ["title", "avg_rating", "rating_count"]

        # Filter movies with minimum ratings
        popular_movies = movie_stats[
            movie_stats["rating_count"] >= min_ratings
        ]
        top_movies = popular_movies.nlargest(15, "avg_rating")

        plt.figure(figsize=(10, 8))
        plt.barh(top_movies["title"], top_movies["avg_rating"])
        plt.title(f"Top 15 Highest Rated Movies (min {min_ratings} ratings)")
        plt.xlabel("Average Rating")
        plt.tight_layout()
        plt.savefig(
            f"{vis_dir}/top_rated_movies.png", dpi=300, bbox_inches="tight"
        )
        plt.show()

    @staticmethod
    def plot_rating_trends(df: pd.DataFrame):
        """Plot rating trends over time"""
        # Convert timestamp to datetime
        df["datetime"] = pd.to_datetime(df["timestamp"], unit="s")
        df["year"] = df["datetime"].dt.year

        # Calculate average rating per year
        yearly_ratings = df.groupby("year")["rating"].mean()

        plt.figure(figsize=(12, 6))
        plt.plot(
            yearly_ratings.index,
            yearly_ratings.values,
            marker="o",
            linewidth=2,
        )
        plt.title("Average Rating Trends Over Time")
        plt.xlabel("Year")
        plt.ylabel("Average Rating")
        plt.grid(True, alpha=0.3)
        plt.tight_layout()
        plt.savefig(
            f"{vis_dir}/rating_trends.png", dpi=300, bbox_inches="tight"
        )
        plt.show()

plot_genre_distribution(movies) staticmethod

Plot distribution of movie genres

Source code in src/visualize.py 
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
@staticmethod
def plot_genre_distribution(movies: pd.DataFrame):
    """Plot distribution of movie genres"""
    # Get all unique genres
    all_genres = set()
    for genres_list in movies["genres"]:
        if isinstance(genres_list, list):
            all_genres.update(genres_list)

    # Count genre occurrences
    genre_counts = {}
    for genre in all_genres:
        if genre != "(no genres listed)":
            genre_counts[genre] = movies[genre].sum()

    # Plot
    plt.figure(figsize=(12, 8))
    genres = list(genre_counts.keys())
    counts = list(genre_counts.values())

    plt.barh(genres, counts)
    plt.title("Movie Genre Distribution")
    plt.xlabel("Number of Movies")
    plt.tight_layout()
    plt.savefig(
        f"{vis_dir}/genre_distribution.png", dpi=300, bbox_inches="tight"
    )
    plt.show()

plot_movies_per_year(movies) staticmethod

Plot number of movies released per year

Source code in src/visualize.py 
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
@staticmethod
def plot_movies_per_year(movies: pd.DataFrame):
    """Plot number of movies released per year"""
    # Extract year from title (assuming format like "Movie Title (Year)")
    movies["year"] = movies["title"].str.extract(r"\((\d{4})\)")
    movies["year"] = pd.to_numeric(movies["year"], errors="coerce")

    # Filter valid years
    movies_with_year = movies.dropna(subset=["year"])
    movies_with_year = movies_with_year[movies_with_year["year"] >= 1900]

    plt.figure(figsize=(12, 6))
    year_counts = movies_with_year["year"].value_counts().sort_index()
    plt.plot(year_counts.index, year_counts.values, linewidth=2)
    plt.title("Number of Movies Released Per Year")
    plt.xlabel("Year")
    plt.ylabel("Number of Movies")
    plt.grid(True, alpha=0.3)
    plt.tight_layout()
    plt.savefig(
        f"{vis_dir}/movies_per_year.png", dpi=300, bbox_inches="tight"
    )
    plt.show()

plot_rating_distribution(ratings) staticmethod

Plot distribution of ratings

Source code in src/visualize.py 
53
54
55
56
57
58
59
60
61
62
63
64
65
@staticmethod
def plot_rating_distribution(ratings: pd.DataFrame):
    """Plot distribution of ratings"""
    plt.figure(figsize=(10, 6))
    sns.histplot(ratings["rating"], bins=10, kde=True)
    plt.title("Rating Distribution")
    plt.xlabel("Rating")
    plt.ylabel("Frequency")
    plt.tight_layout()
    plt.savefig(
        f"{vis_dir}/rating_distribution.png", dpi=300, bbox_inches="tight"
    )
    plt.show()

Plot rating trends over time

Source code in src/visualize.py 
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
@staticmethod
def plot_rating_trends(df: pd.DataFrame):
    """Plot rating trends over time"""
    # Convert timestamp to datetime
    df["datetime"] = pd.to_datetime(df["timestamp"], unit="s")
    df["year"] = df["datetime"].dt.year

    # Calculate average rating per year
    yearly_ratings = df.groupby("year")["rating"].mean()

    plt.figure(figsize=(12, 6))
    plt.plot(
        yearly_ratings.index,
        yearly_ratings.values,
        marker="o",
        linewidth=2,
    )
    plt.title("Average Rating Trends Over Time")
    plt.xlabel("Year")
    plt.ylabel("Average Rating")
    plt.grid(True, alpha=0.3)
    plt.tight_layout()
    plt.savefig(
        f"{vis_dir}/rating_trends.png", dpi=300, bbox_inches="tight"
    )
    plt.show()

plot_top_rated_movies(df, min_ratings=50) staticmethod

Plot top rated movies with minimum number of ratings

Source code in src/visualize.py 
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
@staticmethod
def plot_top_rated_movies(df: pd.DataFrame, min_ratings=50):
    """Plot top rated movies with minimum number of ratings"""
    # Calculate average rating and count for each movie
    movie_stats = (
        df.groupby("title")
        .agg({"rating": ["mean", "count"]})
        .reset_index()
    )

    # Flatten column names
    movie_stats.columns = ["title", "avg_rating", "rating_count"]

    # Filter movies with minimum ratings
    popular_movies = movie_stats[
        movie_stats["rating_count"] >= min_ratings
    ]
    top_movies = popular_movies.nlargest(15, "avg_rating")

    plt.figure(figsize=(10, 8))
    plt.barh(top_movies["title"], top_movies["avg_rating"])
    plt.title(f"Top 15 Highest Rated Movies (min {min_ratings} ratings)")
    plt.xlabel("Average Rating")
    plt.tight_layout()
    plt.savefig(
        f"{vis_dir}/top_rated_movies.png", dpi=300, bbox_inches="tight"
    )
    plt.show()

create_all_visualizations()

Create all visualizations

Source code in src/visualize.py 
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
def create_all_visualizations():
    """Create all visualizations"""
    print("Creating visualizations...")

    viz = Visualizer()

    print("1. Genre distribution...")
    viz.plot_genre_distribution(movies)

    print("2. Rating distribution...")
    viz.plot_rating_distribution(ratings)

    print("3. Movies per year...")
    viz.plot_movies_per_year(movies)

    print("4. Top rated movies...")
    viz.plot_top_rated_movies(df)

    print("5. Rating trends...")
    viz.plot_rating_trends(df)

    print("All visualizations saved!")