Duplicate from rushankg/test-streamlit

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.streamlit/config.toml

@@ -0,0 +1,9 @@
+[theme] # You have to add this line
+
+primaryColor = '#FFFFFF' # Palo Alto Green
+
+backgroundColor = '#820000' # Cardinal Red
+
+secondaryBackgroundColor = '#820000' # Cardinal Red
+
+textColor = '#FFFFFF' # White

README.md

@@ -0,0 +1,14 @@
+---
+title: Test Streamlit
+emoji: 🦀
+colorFrom: green
+colorTo: red
+sdk: streamlit
+sdk_version: 1.25.0
+app_file: app.py
+pinned: false
+license: cc-by-2.0
+duplicated_from: rushankg/test-streamlit
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,67 @@
+import streamlit as st
+import pickle
+import pandas as pd
+import torch
+import numpy as np
+
+cosine_scores = pickle.load(open('cosine_scores.pkl','rb'))
+coursedf = pd.read_pickle('course_df.pkl')          # course_df uses titles to generate course recommendations
+course_df_new = pd.read_pickle('course_df_new.pkl') #course_df_new makes recommendations using the entire description
+
+course_title_list = [i + ": " + j for i, j in zip(coursedf['ref'].to_list(), coursedf['title'].to_list())]
+
+def get_random_course():
+    row=coursedf.sample(1)
+    return row['ref'], row['title'] 
+
+def recommend(index):
+    pairs = {}
+
+    for i in range(len(coursedf)):
+        pairs[coursedf.iloc[i,1]]=cosine_scores[index][i]
+
+    sorttemp = sorted(pairs.items(), key=lambda x:x[1], reverse=True)
+    sorted_final = dict(sorttemp[1:31])
+
+    return list(sorted_final.keys())
+
+st.set_page_config(page_title='DiscoverCourses', page_icon=':bird:')
+st.header('DiscoverCourses')
+st.write('')
+
+selected_course = st.selectbox('Pick a course from the dropdown:',course_title_list)
+
+container = st.container()
+maincol1, maincol2 = container.columns(2)
+st.write('')
+
+if maincol1.button('Recommend by title',use_container_width=True):
+    output=recommend(np.where((coursedf['ref']+": "+coursedf['title']) == selected_course)[0][0])
+    for result in output:
+        index=np.where(coursedf['title'] == result)[0][0]
+        course_id=coursedf.iloc[index,0]
+        st.subheader(course_id+": "+result)
+        with st.expander("See description"):
+            st.write(course_df_new.iloc[index,3]) #Using the new coursedf because it has proper descriptions for each course
+        link = "[ExploreCourses](https://explorecourses.stanford.edu/search?q="+course_id+"+"+result.replace(" ","+")+")"
+        st.markdown(link, unsafe_allow_html=True)
+        link = "[Carta](https://carta-beta.stanford.edu/results/"+course_id+")"
+        st.markdown(link, unsafe_allow_html=True)
+        st.divider()
+        
+if maincol2.button('Recommend by description',use_container_width=True):
+    index_new=np.where((coursedf['ref']+": "+coursedf['title']) == selected_course)[0][0]
+    rec_list=course_df_new.iloc[index_new,2]
+    for result in rec_list:
+        index=np.where(coursedf['title'] == result)[0][0]
+        course_id=coursedf.iloc[index,0]
+        st.subheader(course_id+": "+result)
+        with st.expander("See description"):
+            st.write(course_df_new.iloc[index,3]) #Using the new coursedf because it has proper descriptions for each course
+        link = "[ExploreCourses](https://explorecourses.stanford.edu/search?q="+course_id+"+"+result.replace(" ","+")+")"
+        st.markdown(link, unsafe_allow_html=True)
+        link = "[Carta](https://carta-beta.stanford.edu/results/"+course_id+")"
+        st.markdown(link, unsafe_allow_html=True)
+        st.divider()
+
+st.write('© 2023 Rushank Goyal. All rights reserved. Source for the all-MiniLM-L6-v2 model: Wang, Wenhui, et al. "MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers." arXiv, 25 Feb. 2020, doi:10.48550/arXiv.2002.10957.')

cosine_scores.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f49c97656d3c2df641600b5560c9c6059dbb388c528b35a5d1d2822df4736d28
+size 258438192

course_df.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a547aaaf1a76a586376e442fa355afc0a3d86ad44b32b3f85e0b4b37d7e1104a
+size 4718547

course_df_new.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:062806ae754b8486468869c17e44d2fcb375cb79a8673e8c48656425997f1f74
+size 7016497

requirements.txt

@@ -0,0 +1,6 @@
+Pillow
+pandas
+numpy
+streamlit
+scikit-learn==1.0.2
+torch