Spaces:
Runtime error
Runtime error
joao-victor-campos
commited on
Commit
•
bb9369a
1
Parent(s):
7150daf
add application file
Browse files- .github/pull_request_template.md +25 -0
- .gitignore +135 -0
- LICENSE +21 -0
- Makefile +55 -0
- app.py +64 -0
- data/input/credits.csv +0 -0
- data/input/titles.csv +0 -0
- recommendation/data_exploration.ipynb +0 -0
- recommendation_app/__init__.py +0 -0
- recommendation_app/__metadata__.py +0 -0
- recommendation_app/core/__inity__.py +0 -0
- recommendation_app/core/data_handler/__inity__.py +0 -0
- recommendation_app/core/data_handler/data_handler.py +42 -0
- recommendation_app/core/model.py +44 -0
- recommendation_app/main.py +64 -0
- requirements.dev.txt +17 -0
- requirements.txt +11 -0
- tests/test_data_handler.py +9 -0
.github/pull_request_template.md
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Description
|
2 |
+
|
3 |
+
Please include a summary of the change and which issue is fixed. Please also include relevant motivation and context. List any dependencies that are required for this change.
|
4 |
+
|
5 |
+
Fixes # (issue)
|
6 |
+
|
7 |
+
## Type of change
|
8 |
+
|
9 |
+
Please delete options that are not relevant.
|
10 |
+
|
11 |
+
- [ ] Bug fix (non-breaking change which fixes an issue)
|
12 |
+
- [ ] New feature (non-breaking change which adds functionality)
|
13 |
+
- [ ] Breaking change (fix or feature that would cause existing functionality to not work as expected)
|
14 |
+
- [ ] This change requires a documentation update
|
15 |
+
|
16 |
+
# Checklist:
|
17 |
+
|
18 |
+
- [ ] My code follows the style guidelines of this project
|
19 |
+
- [ ] I have performed a self-review of my own code
|
20 |
+
- [ ] I have commented my code, particularly in hard-to-understand areas
|
21 |
+
- [ ] I have made corresponding changes to the documentation
|
22 |
+
- [ ] My changes generate no new warnings
|
23 |
+
- [ ] I have added tests that prove my fix is effective or that my feature works
|
24 |
+
- [ ] New and existing unit tests pass locally with my changes
|
25 |
+
- [ ] Any dependent changes have been merged and published in downstream modules
|
.gitignore
ADDED
@@ -0,0 +1,135 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Byte-compiled / optimized / DLL files
|
2 |
+
pycache/
|
3 |
+
*.py[cod]
|
4 |
+
*$py.class
|
5 |
+
|
6 |
+
# C extensions
|
7 |
+
*.so
|
8 |
+
|
9 |
+
# Distribution / packaging
|
10 |
+
.Python
|
11 |
+
build/
|
12 |
+
develop-eggs/
|
13 |
+
dist/
|
14 |
+
downloads/
|
15 |
+
eggs/
|
16 |
+
.eggs/
|
17 |
+
lib/
|
18 |
+
lib64/
|
19 |
+
parts/
|
20 |
+
sdist/
|
21 |
+
var/
|
22 |
+
wheels/
|
23 |
+
pip-wheel-metadata/
|
24 |
+
share/python-wheels/
|
25 |
+
*.egg-info/
|
26 |
+
.installed.cfg
|
27 |
+
*.egg
|
28 |
+
MANIFEST
|
29 |
+
|
30 |
+
# PyInstaller
|
31 |
+
# Usually these files are written by a python script from a template
|
32 |
+
# before PyInstaller builds the exe, so as to inject date/other infos into it.
|
33 |
+
*.manifest
|
34 |
+
.spec
|
35 |
+
|
36 |
+
# Installer logs
|
37 |
+
pip-log.txt
|
38 |
+
pip-delete-this-directory.txt
|
39 |
+
|
40 |
+
# Unit test / coverage reports
|
41 |
+
htmlcov/
|
42 |
+
.tox/
|
43 |
+
.nox/
|
44 |
+
.coverage
|
45 |
+
.coverage.
|
46 |
+
.cache
|
47 |
+
nosetests.xml
|
48 |
+
coverage.xml
|
49 |
+
*.cover
|
50 |
+
*.py,cover
|
51 |
+
.hypothesis/
|
52 |
+
.pytest_cache/
|
53 |
+
|
54 |
+
# Translations
|
55 |
+
*.mo
|
56 |
+
*.pot
|
57 |
+
|
58 |
+
# Django stuff:
|
59 |
+
*.log
|
60 |
+
local_settings.py
|
61 |
+
db.sqlite3
|
62 |
+
db.sqlite3-journal
|
63 |
+
|
64 |
+
# Flask stuff:
|
65 |
+
instance/
|
66 |
+
.webassets-cache
|
67 |
+
|
68 |
+
# Scrapy stuff:
|
69 |
+
.scrapy
|
70 |
+
|
71 |
+
# Sphinx documentation
|
72 |
+
docs/_build/
|
73 |
+
|
74 |
+
# PyBuilder
|
75 |
+
target/
|
76 |
+
|
77 |
+
# Jupyter Notebook
|
78 |
+
.ipynb_checkpoints
|
79 |
+
|
80 |
+
# IPython
|
81 |
+
profile_default/
|
82 |
+
ipython_config.py
|
83 |
+
|
84 |
+
# pyenv
|
85 |
+
.python-version
|
86 |
+
|
87 |
+
# pipenv
|
88 |
+
# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
|
89 |
+
# However, in case of collaboration, if having platform-specific dependencies or dependencies
|
90 |
+
# having no cross-platform support, pipenv may install dependencies that don't work, or not
|
91 |
+
# install all needed dependencies.
|
92 |
+
#Pipfile.lock
|
93 |
+
|
94 |
+
# PEP 582; used by e.g. github.com/David-OConnor/pyflow
|
95 |
+
pypackages/
|
96 |
+
|
97 |
+
# Celery stuff
|
98 |
+
celerybeat-schedule
|
99 |
+
celerybeat.pid
|
100 |
+
|
101 |
+
# SageMath parsed files
|
102 |
+
*.sage.py
|
103 |
+
|
104 |
+
# Environments
|
105 |
+
.env
|
106 |
+
.venv
|
107 |
+
env/
|
108 |
+
venv/
|
109 |
+
ENV/
|
110 |
+
env.bak/
|
111 |
+
venv.bak/
|
112 |
+
|
113 |
+
# Spyder project settings
|
114 |
+
.spyderproject
|
115 |
+
.spyproject
|
116 |
+
|
117 |
+
# Rope project settings
|
118 |
+
.ropeproject
|
119 |
+
|
120 |
+
# mkdocs documentation
|
121 |
+
/site
|
122 |
+
|
123 |
+
# mypy
|
124 |
+
.mypy_cache/
|
125 |
+
.dmypy.json
|
126 |
+
dmypy.json
|
127 |
+
|
128 |
+
# Pyre type checker
|
129 |
+
.pyre/
|
130 |
+
|
131 |
+
.vscode/
|
132 |
+
|
133 |
+
.deb
|
134 |
+
|
135 |
+
data/output/
|
LICENSE
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
MIT License
|
2 |
+
|
3 |
+
Copyright (c) 2022 João Victor Campos
|
4 |
+
|
5 |
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
6 |
+
of this software and associated documentation files (the "Software"), to deal
|
7 |
+
in the Software without restriction, including without limitation the rights
|
8 |
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
9 |
+
copies of the Software, and to permit persons to whom the Software is
|
10 |
+
furnished to do so, subject to the following conditions:
|
11 |
+
|
12 |
+
The above copyright notice and this permission notice shall be included in all
|
13 |
+
copies or substantial portions of the Software.
|
14 |
+
|
15 |
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
16 |
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
17 |
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
18 |
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
19 |
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
20 |
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
21 |
+
SOFTWARE.
|
Makefile
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# globals
|
2 |
+
VERSION := $(shell grep __version__ recommendation_app/__metadata__.py | head -1 | cut -d \" -f2 | cut -d \' -f2)
|
3 |
+
|
4 |
+
.PHONY: requirements-dev
|
5 |
+
## install development requirements
|
6 |
+
requirements-dev:
|
7 |
+
@python -m pip install -U -r requirements.dev.txt
|
8 |
+
|
9 |
+
.PHONY: requirements-minimum
|
10 |
+
## install prod requirements
|
11 |
+
requirements-minimum:
|
12 |
+
@python -m pip install -U -r requirements.txt
|
13 |
+
|
14 |
+
.PHONY: requirements
|
15 |
+
## install requirements
|
16 |
+
requirements: requirements-dev requirements-minimum
|
17 |
+
|
18 |
+
.PHONY: style-check
|
19 |
+
## run code style checks with black
|
20 |
+
style-check:
|
21 |
+
@echo ""
|
22 |
+
@echo "Code Style"
|
23 |
+
@echo "=========="
|
24 |
+
@echo ""
|
25 |
+
@python -m black --check --exclude="build/|buck-out/|dist/|_build/|pip/|\.pip/|\.git/|\.hg/|\.mypy_cache/|\.tox/|\.venv/" . && echo "\n\nSuccess" || (echo "\n\nFailure\n\nRun \"make black\" to apply style formatting to your code"; exit 1)
|
26 |
+
|
27 |
+
.PHONY: quality-check
|
28 |
+
## run code quality checks with flake8
|
29 |
+
quality-check:
|
30 |
+
@echo ""
|
31 |
+
@echo "Flake 8"
|
32 |
+
@echo "======="
|
33 |
+
@echo ""
|
34 |
+
@python -m flake8 && echo "Success"
|
35 |
+
@echo ""
|
36 |
+
|
37 |
+
.PHONY: type-check
|
38 |
+
## run code type checks with mypy
|
39 |
+
type-check:
|
40 |
+
@echo ""
|
41 |
+
@echo "Mypy"
|
42 |
+
@echo "======="
|
43 |
+
@echo ""
|
44 |
+
@python -m mypy --install-types --non-interactive recommendation_app && echo "Success"
|
45 |
+
@echo ""
|
46 |
+
|
47 |
+
.PHONY: checks
|
48 |
+
## run all code checks
|
49 |
+
checks: style-check quality-check type-check
|
50 |
+
|
51 |
+
.PHONY: apply-style
|
52 |
+
## fix stylistic errors with black and isort
|
53 |
+
apply-style:
|
54 |
+
@python -m black --exclude="build/|buck-out/|dist/|_build/|pip/|\\.pip/|\.git/|\.hg/|\.mypy_cache/|\.tox/|\.venv/" .
|
55 |
+
@python -m isort recommendation_app/ tests/
|
app.py
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import gradio as gr
|
2 |
+
import pandas as pd
|
3 |
+
from recommendation_app.core.data_handler.data_handler import DataHandler
|
4 |
+
from recommendation_app.core.model import Model
|
5 |
+
|
6 |
+
PATH = "../netflix-recommendation-app/data/output/df_titles.csv"
|
7 |
+
df2 = pd.read_csv(PATH)
|
8 |
+
movie_names = df2["title"].tolist()
|
9 |
+
|
10 |
+
|
11 |
+
def gradio(movie_name, n_rec):
|
12 |
+
if __name__ == "__main__":
|
13 |
+
PATH = "../netflix-recommendation-app/data/output/df_titles.csv"
|
14 |
+
features = [
|
15 |
+
"type",
|
16 |
+
"release_year",
|
17 |
+
"age_certification",
|
18 |
+
"runtime",
|
19 |
+
"seasons",
|
20 |
+
"imdb_score",
|
21 |
+
"tmdb_popularity",
|
22 |
+
"tmdb_score",
|
23 |
+
"genres_transformed",
|
24 |
+
"production_countries_transformed",
|
25 |
+
]
|
26 |
+
df = pd.read_csv(PATH)
|
27 |
+
df_model = df.copy()
|
28 |
+
df_model = df_model[features]
|
29 |
+
x = DataHandler(df_model)
|
30 |
+
numeric_features = [
|
31 |
+
"release_year",
|
32 |
+
"runtime",
|
33 |
+
"seasons",
|
34 |
+
"imdb_score",
|
35 |
+
"tmdb_popularity",
|
36 |
+
"tmdb_score",
|
37 |
+
]
|
38 |
+
x.normalize(numeric_features)
|
39 |
+
categorical_features = [
|
40 |
+
"age_certification",
|
41 |
+
"type",
|
42 |
+
"genres_transformed",
|
43 |
+
"production_countries_transformed",
|
44 |
+
]
|
45 |
+
x.one_hot_encode(categorical_features)
|
46 |
+
# print(x.one_hot_encode(categorical_features))
|
47 |
+
# print(x.df)
|
48 |
+
mdl = Model(x.df)
|
49 |
+
n_rec = int(n_rec)
|
50 |
+
movie_name = str(movie_name)
|
51 |
+
movie_id = df.index[df["title"] == movie_name].tolist()
|
52 |
+
print(movie_id)
|
53 |
+
recommendations = mdl.recommend(movie_id, n_rec)
|
54 |
+
top_index = list(recommendations.index)[1:]
|
55 |
+
print(df[["title", "description"]].loc[top_index])
|
56 |
+
return df[["title", "description"]].loc[top_index]
|
57 |
+
|
58 |
+
|
59 |
+
app = gr.Interface(
|
60 |
+
fn=gradio,
|
61 |
+
inputs=[gr.Dropdown(choices=movie_names), gr.inputs.Number()],
|
62 |
+
outputs=[gr.outputs.Dataframe()],
|
63 |
+
)
|
64 |
+
app.launch()
|
data/input/credits.csv
ADDED
The diff for this file is too large to render.
See raw diff
|
|
data/input/titles.csv
ADDED
The diff for this file is too large to render.
See raw diff
|
|
recommendation/data_exploration.ipynb
ADDED
The diff for this file is too large to render.
See raw diff
|
|
recommendation_app/__init__.py
ADDED
File without changes
|
recommendation_app/__metadata__.py
ADDED
File without changes
|
recommendation_app/core/__inity__.py
ADDED
File without changes
|
recommendation_app/core/data_handler/__inity__.py
ADDED
File without changes
|
recommendation_app/core/data_handler/data_handler.py
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from typing import List
|
2 |
+
|
3 |
+
import numpy as np
|
4 |
+
import pandas as pd
|
5 |
+
from sklearn import preprocessing
|
6 |
+
|
7 |
+
|
8 |
+
class DataHandler:
|
9 |
+
def __init__(self, df: pd.DataFrame) -> None:
|
10 |
+
self.df = df
|
11 |
+
|
12 |
+
def normalize(self, features: List) -> pd.DataFrame:
|
13 |
+
"""Normalize a list of features from the DataFrame inplace.
|
14 |
+
|
15 |
+
Args:
|
16 |
+
df (pd.DataFrame): DataFrame to normalize the columns.
|
17 |
+
features (List): List of DataFrame column names.
|
18 |
+
|
19 |
+
Returns:
|
20 |
+
pd.DataFrame: DataFrame with normalized columns.
|
21 |
+
"""
|
22 |
+
normalized_arr = preprocessing.normalize(self.df[features], axis=0)
|
23 |
+
self.df[features] = normalized_arr
|
24 |
+
return self.df
|
25 |
+
|
26 |
+
def one_hot_encode(self, features: List) -> pd.DataFrame:
|
27 |
+
"""One Hot Encode a list of features from the DataFrame inplace.
|
28 |
+
|
29 |
+
Args:
|
30 |
+
df (pd.DataFrame): DataFrame to one hot encode the columns.
|
31 |
+
features (List): List of DataFrame column names.
|
32 |
+
|
33 |
+
Returns:
|
34 |
+
pd.DataFrame: DataFrame with one hot encoded columns.
|
35 |
+
"""
|
36 |
+
for i in features:
|
37 |
+
ohe_df = pd.get_dummies(self.df[i])
|
38 |
+
print(ohe_df)
|
39 |
+
ohe_df.reset_index(drop=True, inplace=True)
|
40 |
+
self.df = pd.concat([self.df, ohe_df], axis=1)
|
41 |
+
self.df.drop(columns=i, inplace=True)
|
42 |
+
return self.df
|
recommendation_app/core/model.py
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from array import array
|
2 |
+
|
3 |
+
import numpy as np
|
4 |
+
import pandas as pd
|
5 |
+
from sklearn.metrics.pairwise import cosine_similarity
|
6 |
+
|
7 |
+
|
8 |
+
class Model:
|
9 |
+
def __init__(self, df: pd.DataFrame):
|
10 |
+
self.df = df
|
11 |
+
|
12 |
+
def movie_similarity(self, chosen_movie: array, sim_movies: array) -> array:
|
13 |
+
"""Calculate the cosine similarity between two vectors.
|
14 |
+
Args:
|
15 |
+
chosen_movie (array): Array with all information about the movie chosen by the user.
|
16 |
+
sim_movies (array): n dimensions array with all movies.
|
17 |
+
Returns:
|
18 |
+
array: Returns the cosine similarity between chosen_movie and sim_array.
|
19 |
+
"""
|
20 |
+
chosen_movie = chosen_movie.reshape(1, -1)
|
21 |
+
# sim_movies = sim_movies.reshape(-1, 6)
|
22 |
+
return cosine_similarity(chosen_movie, sim_movies, dense_output=True)
|
23 |
+
|
24 |
+
def recommend(self, movie_id: str, n_rec: int) -> pd.DataFrame:
|
25 |
+
"""Returns nlargest similarity movies based on movie_id.
|
26 |
+
Args:
|
27 |
+
movie_id (str): Name of the movie to be compared.
|
28 |
+
n_rec (int): Number of movies the user wants.
|
29 |
+
Returns:
|
30 |
+
pd.DataFrame: Dataframe with the n_rec recommendations.
|
31 |
+
"""
|
32 |
+
movie_info = self.df.loc[movie_id].values
|
33 |
+
x = self.movie_similarity(movie_info, self.df.values)
|
34 |
+
|
35 |
+
# x.reshape(1, -1)
|
36 |
+
y = x.tolist()[0]
|
37 |
+
print(y)
|
38 |
+
self.df["similarity"] = y
|
39 |
+
print(self.df)
|
40 |
+
# movie_info = self.df.loc[movie_id].values
|
41 |
+
# self.df['similarity'] = self.df.apply(self.movie_similarity(movie_info,
|
42 |
+
# self.df.values)))
|
43 |
+
|
44 |
+
return self.df.nlargest(columns="similarity", n=n_rec + 1)
|
recommendation_app/main.py
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import gradio as gr
|
2 |
+
import pandas as pd
|
3 |
+
from core.data_handler.data_handler import DataHandler
|
4 |
+
from core.model import Model
|
5 |
+
|
6 |
+
PATH = "../netflix-recommendation-app/data/output/df_titles.csv"
|
7 |
+
df2 = pd.read_csv(PATH)
|
8 |
+
movie_names = df2["title"].tolist()
|
9 |
+
|
10 |
+
|
11 |
+
def gradio(movie_name, n_rec):
|
12 |
+
if __name__ == "__main__":
|
13 |
+
PATH = "../netflix-recommendation-app/data/output/df_titles.csv"
|
14 |
+
features = [
|
15 |
+
"type",
|
16 |
+
"release_year",
|
17 |
+
"age_certification",
|
18 |
+
"runtime",
|
19 |
+
"seasons",
|
20 |
+
"imdb_score",
|
21 |
+
"tmdb_popularity",
|
22 |
+
"tmdb_score",
|
23 |
+
"genres_transformed",
|
24 |
+
"production_countries_transformed",
|
25 |
+
]
|
26 |
+
df = pd.read_csv(PATH)
|
27 |
+
df_model = df.copy()
|
28 |
+
df_model = df_model[features]
|
29 |
+
x = DataHandler(df_model)
|
30 |
+
numeric_features = [
|
31 |
+
"release_year",
|
32 |
+
"runtime",
|
33 |
+
"seasons",
|
34 |
+
"imdb_score",
|
35 |
+
"tmdb_popularity",
|
36 |
+
"tmdb_score",
|
37 |
+
]
|
38 |
+
x.normalize(numeric_features)
|
39 |
+
categorical_features = [
|
40 |
+
"age_certification",
|
41 |
+
"type",
|
42 |
+
"genres_transformed",
|
43 |
+
"production_countries_transformed",
|
44 |
+
]
|
45 |
+
x.one_hot_encode(categorical_features)
|
46 |
+
# print(x.one_hot_encode(categorical_features))
|
47 |
+
# print(x.df)
|
48 |
+
mdl = Model(x.df)
|
49 |
+
n_rec = int(n_rec)
|
50 |
+
movie_name = str(movie_name)
|
51 |
+
movie_id = df.index[df["title"] == movie_name].tolist()
|
52 |
+
print(movie_id)
|
53 |
+
recommendations = mdl.recommend(movie_id, n_rec)
|
54 |
+
top_index = list(recommendations.index)[1:]
|
55 |
+
print(df[["title", "description"]].loc[top_index])
|
56 |
+
return df[["title", "description"]].loc[top_index]
|
57 |
+
|
58 |
+
|
59 |
+
app = gr.Interface(
|
60 |
+
fn=gradio,
|
61 |
+
inputs=[gr.Dropdown(choices=movie_names), gr.inputs.Number()],
|
62 |
+
outputs=[gr.outputs.Dataframe()],
|
63 |
+
)
|
64 |
+
app.launch()
|
requirements.dev.txt
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# setup
|
2 |
+
setuptools
|
3 |
+
wheel
|
4 |
+
|
5 |
+
# tests
|
6 |
+
pytest
|
7 |
+
pytest-cov
|
8 |
+
|
9 |
+
# code quality
|
10 |
+
black
|
11 |
+
isort
|
12 |
+
flake8
|
13 |
+
flake8-isort
|
14 |
+
flake8-docstrings
|
15 |
+
pep8-naming
|
16 |
+
mypy
|
17 |
+
black[jupyter]
|
requirements.txt
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
ipykernel==6.15.1
|
2 |
+
pandas
|
3 |
+
seaborn
|
4 |
+
matplotlib
|
5 |
+
pandas_profiling
|
6 |
+
ipywidgets
|
7 |
+
plotly
|
8 |
+
sklearn
|
9 |
+
numpy
|
10 |
+
jupyter
|
11 |
+
gradio
|
tests/test_data_handler.py
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
df3 = pd.DataFrame(
|
2 |
+
[["c", 3, 10, "cat"], ["d", 4, 50, "dog"]],
|
3 |
+
columns=["letter", "number", "number2", "animal"],
|
4 |
+
)
|
5 |
+
|
6 |
+
|
7 |
+
x = DataHandler(df3)
|
8 |
+
x.normalize(["number", "number2"])
|
9 |
+
print(x.one_hot_encode(["letter", "animal"]))
|