Py.Cafe

kdheepak/

movies-dashboard

DocsPricing
  • app.py
  • requirements.txt
app.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
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
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
# -*- coding: utf-8 -*-
import param as pm
import pandas as pd
import panel as pn
import holoviews as hv

pd.options.mode.copy_on_write = True
pd.options.future.no_silent_downcasting = True

pn.extension(
    "tabulator",
    sizing_mode="stretch_width",
    notifications=True,
    throttled=True,
)
hv.extension("bokeh")


@pn.cache
def get_data():
    title_basics = pd.read_csv(
        "https://datasets.imdbws.com/title.basics.tsv.gz",
        sep="\t",
        dtype={
            "tconst": "object",
            "primaryTitle": "object",
            "titleType": "object",
            "runtimeMinutes": "object",
            "startYear": "object",
        },
        usecols=[
            "tconst",
            "titleType",
            "primaryTitle",
            "runtimeMinutes",
            "startYear",
            "genres",
        ],
        na_values="\\N",
    ).query("titleType == 'movie'")
    title_ratings = pd.read_csv(
        "https://datasets.imdbws.com/title.ratings.tsv.gz",
        sep="\t",
        dtype={"tconst": "object", "averageRating": "float64", "numVotes": "int64"},
        usecols=["tconst", "averageRating", "numVotes"],
    )
    movies = title_basics.merge(title_ratings, on="tconst").dropna()
    movies["startYear"] = pd.to_numeric(movies["startYear"], downcast="integer")
    movies["runtimeMinutes"] = pd.to_numeric(movies["runtimeMinutes"], downcast="integer")
    movies["genres"] = movies["genres"].str.split(",")
    movies = movies.explode("genres")
    return movies

class Movies(pm.Parameterized):
    df = pm.DataFrame()
    filtered_df = pm.DataFrame()
    year_range = pm.Range()
    ratings_range = pm.Range()
    runtime_range = pm.Range()
    genre = pm.Selector()

    def _preprocess_data(self):
        self.df = get_data()

    @pm.depends("df", watch=True, on_init=True)
    def _update_bounds(self):
        if self.df is None:
            return

        self.param.year_range.bounds = (
            int(self.df.startYear.min()),
            int(self.df.startYear.max()),
        )
        self.year_range = (
            int(self.df.startYear.min()),
            int(self.df.startYear.max()),
        )

        self.param.ratings_range.bounds = (0, 10)
        self.ratings_range = (0, 10)

        self.param.runtime_range.bounds = (
            int(self.df.runtimeMinutes.min()),
            int(self.df.runtimeMinutes.max()),
        )

        self.runtime_range = (
            int(self.df.runtimeMinutes.min()),
            int(self.df.runtimeMinutes.max()),
        )

        self.param.genre.objects = list(self.df.genres.unique())
        self.genre = self.df.genres.unique()[0]

    @pm.depends(
        "df",
        "year_range",
        "ratings_range",
        "runtime_range",
        "genre",
        watch=True,
        on_init=True,
    )
    def _update_table(self):
        if self.year_range is None or self.ratings_range is None or self.runtime_range is None:
            return self.df
        df, year_range, ratings_range, runtime_range, genre = (
            self.df,
            self.year_range,
            self.ratings_range,
            self.runtime_range,
            self.genre,
        )
        self.filtered_df = (
            df.query(f"genres == '{genre}'")
            .query(f"startYear >= {year_range[0]}")
            .query(f"startYear <= {year_range[-1]}")
            .query(f"averageRating >= {ratings_range[0]}")
            .query(f"averageRating <= {ratings_range[-1]}")
            .query(f"runtimeMinutes >= {runtime_range[0]}")
            .query(f"runtimeMinutes <= {runtime_range[-1]}")
        )

    @pm.depends("filtered_df")
    def _update_plot(self):
        plot = hv.BoxWhisker(self.filtered_df, kdims=["startYear"], vdims=["averageRating"],).opts(
            width=900,
            height=400,
            title=f"IMDb Movies - {self.genre}",
            xlabel="Year",
            ylabel="IMDb Rating",
            ylim=(0, 10),
            xrotation=90,
        )

        return plot

    def panel(self):
        table = pn.widgets.Tabulator(
            self.param.filtered_df,
            pagination="remote",
            page_size=10,
        )
        genres = pn.widgets.Select.from_param(self.param.genre)
        plot = self._update_plot

        layout = pn.Column(
            pn.Row(
                self.param.ratings_range,
                self.param.year_range,
                self.param.runtime_range,
            ),
            pn.Row(genres),
            pn.Tabs(("Visualization", hv.DynamicMap(plot)), ("Data", table)),
        )
        return layout


app = Movies()
template = pn.template.BootstrapTemplate(
    title="Movies Dashboard",
    sidebar=pn.Card(
        pn.pane.Markdown(
            r"""
# Movies Dashboard

This panel downloads IMDb database and visualizes average rating for per genre for each year.
                                     """
        )
    ),
)
template.main.append(pn.Card(app.panel, title="Movies Dashboard"))

pn.state.onload(app._preprocess_data)

template.servable()