Spaces:
Runtime error
Runtime error
Commit
•
a992504
1
Parent(s):
1ce7f5c
upload files
Browse files- .gitattributes +3 -0
- Images/IMG-20220413-WA0005.jpg +0 -0
- Images/analytics.png +0 -0
- Images/pipeline.png +0 -0
- app.py +167 -0
- videos/Fairly-used.mp4 +3 -0
- videos/movie-recommender.mp4 +3 -0
- videos/music-mood.mp4 +3 -0
- videos/requirements.txt +1 -0
.gitattributes
CHANGED
@@ -35,3 +35,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
35 |
my_portfolio/videos/Fairly-used.mp4 filter=lfs diff=lfs merge=lfs -text
|
36 |
my_portfolio/videos/movie-recommender.mp4 filter=lfs diff=lfs merge=lfs -text
|
37 |
my_portfolio/videos/music-mood.mp4 filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
35 |
my_portfolio/videos/Fairly-used.mp4 filter=lfs diff=lfs merge=lfs -text
|
36 |
my_portfolio/videos/movie-recommender.mp4 filter=lfs diff=lfs merge=lfs -text
|
37 |
my_portfolio/videos/music-mood.mp4 filter=lfs diff=lfs merge=lfs -text
|
38 |
+
videos/Fairly-used.mp4 filter=lfs diff=lfs merge=lfs -text
|
39 |
+
videos/movie-recommender.mp4 filter=lfs diff=lfs merge=lfs -text
|
40 |
+
videos/music-mood.mp4 filter=lfs diff=lfs merge=lfs -text
|
Images/IMG-20220413-WA0005.jpg
ADDED
![]() |
Images/analytics.png
ADDED
![]() |
Images/pipeline.png
ADDED
![]() |
app.py
ADDED
@@ -0,0 +1,167 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import streamlit as st
|
2 |
+
from PIL import Image
|
3 |
+
|
4 |
+
|
5 |
+
|
6 |
+
|
7 |
+
st.title(' _Welcome to my Projects Portfolio_ ')
|
8 |
+
|
9 |
+
with st.sidebar:
|
10 |
+
image = Image.open("/Images/IMG-20220413-WA0005.jpg")
|
11 |
+
st.image(image)
|
12 |
+
st.subheader("Interest")
|
13 |
+
st.markdown("""
|
14 |
+
- Football
|
15 |
+
- Reading
|
16 |
+
- Cycling
|
17 |
+
""")
|
18 |
+
|
19 |
+
|
20 |
+
|
21 |
+
col1, col2 = st.columns(2)
|
22 |
+
with col1:
|
23 |
+
st.write("Name: Abubakar Muhammed Muktar")
|
24 |
+
st.write("Status: Masters Student, Data Science & Analytics")
|
25 |
+
st.write("School: EPITA")
|
26 |
+
with col2:
|
27 |
+
st.write("Strength: Serial learning, knowing I can always improve.")
|
28 |
+
st.write("Favourite Quote: In God we trust, Everyone else bring data!")
|
29 |
+
st.header("Data Science and Engineering Project Section")
|
30 |
+
with st.expander("PROJECT 1: Fairly Used Car Prediction Platform"):
|
31 |
+
st.subheader('Fairly Used Car Prediction Platform')
|
32 |
+
st.write("This project is ...")
|
33 |
+
st.markdown("""
|
34 |
+
- Created a price estimation model for fairly used car using Linear Regression
|
35 |
+
- Developed a web platform Using Streamlit and deployed the model as a service\n
|
36 |
+
- Platform can predict take direct input from a user or take a csv file and run predictions on them\n
|
37 |
+
- Used postgres to save user predictions and user can query past prediction from the database\n
|
38 |
+
- Airflow to schedule data ingestion and prediction jobs\n
|
39 |
+
- Used Grafana to monitor model and MLFlow for retraining.
|
40 |
+
""")
|
41 |
+
|
42 |
+
st.markdown("[Project CODE](https://github.com/sadiksmart0/Used-Car-ML)")
|
43 |
+
video_file = open('C:/Users/A.M. MUKTAR/my_portfolio/videos/Fairly-used.mp4', 'rb')
|
44 |
+
video_bytes = video_file.read()
|
45 |
+
st.video(video_bytes)
|
46 |
+
|
47 |
+
with st.expander("PROJECT 2: Music Emotion Recognition and Recommendatation."):
|
48 |
+
st.subheader('Music Emotion Recognition and Recommendatation')
|
49 |
+
st.write("This project is ...")
|
50 |
+
st.markdown("""
|
51 |
+
- Collaborated and developed a state-of-the-art deep learning model using BERT and gensims Doc2Vec for recognizing song emotion and give recommendations based on that given lyrics, song title and artist name.
|
52 |
+
- Deployed the model on Heroku and serve the it using FastApi.
|
53 |
+
- Develop and deployed the app on streamlit.
|
54 |
+
- Presented the work as part of our masters thesis.
|
55 |
+
""")
|
56 |
+
|
57 |
+
st.markdown("[Project CODE](https://github.com/anthonybassaf/music-mood-recognition)")
|
58 |
+
video_file = open('videos/music-mood.mp4', 'rb')
|
59 |
+
video_bytes = video_file.read()
|
60 |
+
st.video(video_bytes)
|
61 |
+
|
62 |
+
with st.expander("PROJECT 3: Brain Tumor Segmentation"):
|
63 |
+
st.subheader('Brain Tumor Segmentation')
|
64 |
+
st.write("This project is ...")
|
65 |
+
st.markdown("""
|
66 |
+
- Created a deep learning model based on the U-net architecture to segment brain tumor images.
|
67 |
+
- Used tensorflow in the implementation.
|
68 |
+
- Engineered the data into desired format.
|
69 |
+
- Evaluated model performance based on Dice loss
|
70 |
+
""")
|
71 |
+
|
72 |
+
st.markdown("[Project CODE](https://github.com/sadiksmart0/Image-seg)")
|
73 |
+
video_file = open('videos/Fairly-used.mp4', 'rb')
|
74 |
+
video_bytes = video_file.read()
|
75 |
+
st.video(video_bytes)
|
76 |
+
|
77 |
+
|
78 |
+
with st.expander("PROJECT 4: Movie Recommendatation system."):
|
79 |
+
st.subheader('Movie Recommendatation system.')
|
80 |
+
st.write("This project is ...")
|
81 |
+
st.markdown("""
|
82 |
+
- Implemented a movie recommendation system for using the cosine similarity, users and movie rating.
|
83 |
+
- Scrape the web for movie posters and details using BeautifulSoup
|
84 |
+
- Built a streamlit app for the recommendation plaform
|
85 |
+
- Employed TF-IDF for tokenization.
|
86 |
+
""")
|
87 |
+
|
88 |
+
st.markdown("[Project CODE](https://github.com/sadiksmart0/Movie-Recommender)")
|
89 |
+
video_file = open('videos/movie-recommender.mp4', 'rb')
|
90 |
+
video_bytes = video_file.read()
|
91 |
+
st.video(video_bytes)
|
92 |
+
|
93 |
+
with st.expander("PROJECT 5: End-to-End Data Engineering Project using Kaggle YouTube Trending Dataset"):
|
94 |
+
st.subheader('Movie Recommendatation system.')
|
95 |
+
st.write("This project intends to manage, simplify, and analyze structured and semi-structured YouTube video data based on video categories and trending metrics in a secure manner.")
|
96 |
+
st.markdown("""
|
97 |
+
- Implement the data pipeline completely using AWS cloud.
|
98 |
+
- Data Lake to hold raw ingested data using Amazon S3
|
99 |
+
- Used AWS Lambda to preprocess the data to a parquet.
|
100 |
+
- Data Warehouse to hold cleansed data in Amazon S3
|
101 |
+
- Catalogue the data using AWS Glue.
|
102 |
+
- Used Athena to query the data.
|
103 |
+
- Used IAM to create rule and policies to allow access accross these tools
|
104 |
+
- Used QuickSight to run analysis on our final data
|
105 |
+
- Used cloudwatch to monitor all of the processes for easy tracking.
|
106 |
+
""")
|
107 |
+
image1 = Image.open("C:/Users/A.M. MUKTAR/my_portfolio/Images/pipeline.png")
|
108 |
+
image2 = Image.open("C:/Users/A.M. MUKTAR/my_portfolio/Images/analytics.png")
|
109 |
+
st.image(image1)
|
110 |
+
st.image(image2)
|
111 |
+
|
112 |
+
|
113 |
+
st.header("Data Analysis Project Section")
|
114 |
+
st.subheader('Pandas')
|
115 |
+
with st.expander("PROJECT 1: Analysis of Ligue 1 From 2010-2021"):
|
116 |
+
st.subheader('Analysis of Ligue 1 From 2010-2021')
|
117 |
+
st.write("This project intends to ...")
|
118 |
+
st.markdown("""
|
119 |
+
- Collaborated and developed a state-of-the-art deep learning model using BERT and gensims Doc2Vec for recognizing song emotion and give recommendations based on that given lyrics, song title and artist name.
|
120 |
+
- Deployed the model on Heroku and serve the it using FastApi.
|
121 |
+
- Develop and deployed the app on streamlit.
|
122 |
+
- Presented the work as part of our masters thesis.
|
123 |
+
""")
|
124 |
+
# # st.image("https://static.streamlit.io/examples/dice.jpg")
|
125 |
+
st.markdown("[Project CODE](https://github.com/sadiksmart0/DataVisualizationProject)")
|
126 |
+
|
127 |
+
|
128 |
+
with st.expander("PROJECT 1: Analysis of Google play Apps"):
|
129 |
+
st.subheader('Analysis of Google play Apps')
|
130 |
+
st.write("This project intends to ...")
|
131 |
+
st.markdown("""
|
132 |
+
- Collaborated and developed a state-of-the-art deep learning model using BERT and gensims Doc2Vec for recognizing song emotion and give recommendations based on that given lyrics, song title and artist name.
|
133 |
+
- Deployed the model on Heroku and serve the it using FastApi.
|
134 |
+
- Develop and deployed the app on streamlit.
|
135 |
+
- Presented the work as part of our masters thesis.
|
136 |
+
""")
|
137 |
+
# # st.image("https://static.streamlit.io/examples/dice.jpg")
|
138 |
+
st.markdown("[Project CODE](https://github.com/sadiksmart0/Android-App-Market/blob/main/Android%20App%20Market.ipynb)")
|
139 |
+
|
140 |
+
|
141 |
+
with st.expander("PROJECT 1: Analysis of Netflix movies"):
|
142 |
+
st.subheader('Analysis of Netflix movies')
|
143 |
+
st.write("This project intends to ...")
|
144 |
+
st.markdown("""
|
145 |
+
- Collaborated and developed a state-of-the-art deep learning model using BERT and gensims Doc2Vec for recognizing song emotion and give recommendations based on that given lyrics, song title and artist name.
|
146 |
+
- Deployed the model on Heroku and serve the it using FastApi.
|
147 |
+
- Develop and deployed the app on streamlit.
|
148 |
+
- Presented the work as part of our masters thesis.
|
149 |
+
""")
|
150 |
+
# # st.image("https://static.streamlit.io/examples/dice.jpg")
|
151 |
+
st.markdown("[Project CODE](https://github.com/sadiksmart0/Netflix-Movies/blob/main/Netflix-Movies.ipynb)")
|
152 |
+
|
153 |
+
|
154 |
+
with st.expander("PROJECT 1: Analysis of Nobel Prize Winners"):
|
155 |
+
st.subheader('Analysis of Nobel Prize Winners')
|
156 |
+
st.write("This project intends to ...")
|
157 |
+
st.markdown("""
|
158 |
+
- Collaborated and developed a state-of-the-art deep learning model using BERT and gensims Doc2Vec for recognizing song emotion and give recommendations based on that given lyrics, song title and artist name.
|
159 |
+
- Deployed the model on Heroku and serve the it using FastApi.
|
160 |
+
- Develop and deployed the app on streamlit.
|
161 |
+
- Presented the work as part of our masters thesis.
|
162 |
+
""")
|
163 |
+
# # st.image("https://static.streamlit.io/examples/dice.jpg")
|
164 |
+
st.markdown("[Project CODE](https://github.com/sadiksmart0/Nobel-Prize/blob/main/Nobel_Prize.ipynb)")
|
165 |
+
|
166 |
+
st.subheader('Tableau')
|
167 |
+
st.subheader('Dataiku')
|
videos/Fairly-used.mp4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a8af4fe6ef00f765a7f1496652d94ee307edef547ea560811daeae7e9b57a71
|
3 |
+
size 27906155
|
videos/movie-recommender.mp4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed8dfb4881b256ce9dea8690195ed66c2a1d56cd40ebdcd00cee4ceb8871e04b
|
3 |
+
size 19207311
|
videos/music-mood.mp4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:422eac24929a3a900f1d4354b7987846dc0948625e5efe2f30e4f97bdee4fef0
|
3 |
+
size 19784159
|
videos/requirements.txt
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
streamlit==1.19.0
|