Upload 5 files

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* 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
+data/custom_dataset.csv filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,80 @@
+import os
+import joblib
+import pandas as pd
+import re
+import nltk
+nltk.download('wordnet')
+nltk.download('stopwords')
+
+import streamlit as st
+import numpy as np
+from nltk.stem import WordNetLemmatizer
+from nltk.corpus import stopwords
+from bs4 import BeautifulSoup
+
+
+# Model saved with Keras model.save()
+MODEL_PATH = 'model/passmodel.pkl'
+TOKENIZER_PATH ='model/tfidfvectorizer.pkl'
+DATA_PATH ='data/custom_dataset.csv'
+
+# loading vectorizer
+vectorizer = joblib.load(TOKENIZER_PATH)
+# loading model
+model = joblib.load(MODEL_PATH)
+#getting stopwords
+stop = stopwords.words('english')
+lemmatizer = WordNetLemmatizer()
+
+
+st.set_page_config(page_title='PDDRS', page_icon='👨‍⚕️',layout = 'wide')
+st.title("💉 Patient Diagnosis and Drug Recommendation System 💉")
+st.header("Enter Patient Condition:")
+raw_text = st.text_input('')
+
+
+def predict(raw_text):
+    global predicted_cond
+    global top_drugs
+    if raw_text != "":
+        clean_text = cleanText(raw_text)
+        clean_lst = [clean_text]
+        tfidf_vect = vectorizer.transform(clean_lst)
+        prediction = model.predict(tfidf_vect)
+        predicted_cond = prediction[0]
+        df = pd.read_csv(DATA_PATH)
+        top_drugs = top_drugs_extractor(predicted_cond,df)
+
+def cleanText(raw_review):
+    # 1. Delete HTML 
+    review_text = BeautifulSoup(raw_review, 'html.parser').get_text()
+    # 2. Make a space
+    letters_only = re.sub('[^a-zA-Z]', ' ', review_text)
+    # 3. lower letters
+    words = letters_only.lower().split()
+    # 5. Stopwords 
+    meaningful_words = [w for w in words if not w in stop]
+    # 6. lemmitization
+    lemmitize_words = [lemmatizer.lemmatize(w) for w in meaningful_words]
+    # 7. space join words
+    return( ' '.join(lemmitize_words))
+
+
+def top_drugs_extractor(condition,df):
+    df_top = df[(df['rating']>=9)&(df['usefulCount']>=90)].sort_values(by = ['rating', 'usefulCount'], ascending = [False, False])
+    drug_lst = df_top[df_top['condition']==condition]['drugName'].head(4).tolist()
+    drug_lst =[*set(drug_lst)]
+    return drug_lst
+
+
+predict_button = st.button("Predict")
+
+if predict_button:
+    predict(raw_text)
+    st.header('Condition Predicted')
+    st.subheader(predicted_cond)
+    st.header('Top Recommended Drugs')
+    for i in range(0,len(top_drugs)):
+        st.subheader(top_drugs[i])
+
+

data/custom_dataset.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39bdc6a910fbfef9b506524047861166c3cf184fa4a3275b8ba958833f3bdbd7
+size 12230423

model/passmodel.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c149cb32e7f154571527d3744e940277d3446e657dc0202b04df3afc54a8e9a0
+size 32354028

model/tfidfvectorizer.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65ffa88aa305ae86fb683d58b397a9260ac1153d3fb381412d4575ac5b14e5e5
+size 27603137

requirements.txt

@@ -0,0 +1,17 @@
+beautifulsoup4==4.11.2
+bokeh==3.0.3
+bs4==0.0.1
+GitPython==3.1.30
+joblib==1.2.0
+nltk==3.8.1
+numpy==1.24.2
+pandas==1.5.3
+regex==2022.10.31
+scikit-learn==1.2.1
+scipy==1.10.0
+SpeechRecognition==1.2.3
+streamlit==1.18.1
+streamlit-bokeh-events==0.1.2
+toml==0.10.2
+tqdm==4.64.1
+