Upload 7 files

.gitattributes

@@ -32,3 +32,5 @@ 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/drugsComTest_raw.csv filter=lfs diff=lfs merge=lfs -text
+data/drugsComTrain_raw.csv filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,81 @@
+import os
+import joblib
+import pandas as pd
+import re
+import nltk
+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/drugsComTrain_raw.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='👨‍⚕️')
+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']>=100)].sort_values(by = ['rating', 'usefulCount'], ascending = [False, False])
+    drug_lst = df_top[df_top['condition']==condition]['drugName'].head(3).tolist()
+    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 3 Drugs Recommended')
+    if top_drugs[0] == top_drugs[1]:
+        st.subheader(top_drugs[0])
+    else:
+        st.subheader(top_drugs[0])
+        st.subheader(top_drugs[1])
+        st.subheader(top_drugs[2])
+
+
+with open('style.css')as f:
+ st.markdown(f"<style>{f.read()}</style>", unsafe_allow_html = True)

data/drugsComTest_raw.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1953e81451b3a43f162e3d438dc1f9c2ee83c9283968a19fce4d3736fdb03eac
+size 28071166

data/drugsComTrain_raw.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc0902b21af0db5b99568a7639ed5f7dad3494a8186a20d05c5b4016c6caedf4
+size 82990470

model/passmodel.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f22688277f5420d94a9be0b56cfca1b898013a96cbdd417cfe80cd51310e7110
+size 74845516

model/tfidfvectorizer.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6caaf578520a735219f0ec253fca79d9c56603b63566388e3f1343226dbd20fd
+size 48320680

style.css

@@ -0,0 +1,4 @@
+#patient-diagnosis-and-drug-recommendation-system{
+    font-size: 40px;
+    text-align: center;
+}