Skip to content

Commit c26ec55

Browse files
wilsonfreitaswilsonfreitas
authored
Merge pull request #192 from jatinkumar604/add-new-file
Add recommendation.ipynb notebook
2 parents 23237ab + bd64e22 commit c26ec55

File tree

1 file changed

+326
-0
lines changed

1 file changed

+326
-0
lines changed

‎recommendation.ipynb‎

Lines changed: 326 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,326 @@
1+
{
2+
"cells": [
3+
{
4+
"cell_type": "markdown",
5+
"metadata": {},
6+
"source": [
7+
"### Recommendation System for Apna_Vaidya\n"
8+
]
9+
},
10+
{
11+
"cell_type": "markdown",
12+
"metadata": {},
13+
"source": [
14+
"#### 1. Rule-Based System"
15+
]
16+
},
17+
{
18+
"cell_type": "code",
19+
"execution_count": null,
20+
"metadata": {},
21+
"outputs": [],
22+
"source": [
23+
"user_profile = None\n",
24+
"user_scenario = None"
25+
]
26+
},
27+
{
28+
"cell_type": "code",
29+
"execution_count": 1,
30+
"metadata": {},
31+
"outputs": [],
32+
"source": [
33+
"def rule_based_recommendation(user_profile, user_scenario):\n",
34+
" if user_scenario == 'Patient with Symptoms':\n",
35+
" return [\"Talk to a Doctor\", \"Verify with a Doctor\", \"Symptom Checker (AI-based)\"]\n",
36+
" elif user_scenario == 'Chronic Condition Management':\n",
37+
" return [\"Get a Prescription\", \"Order Medication\", \"Talk to a Doctor\", \"Talk to a Pharmacist\", \"Health Coach Consultation\"]\n",
38+
" elif user_scenario == 'New Medication Inquiry':\n",
39+
" return [\"Talk to a Doctor\", \"Talk to a Pharmacist\", \"Medication Information (AI-based)\"]\n",
40+
" elif user_scenario == 'Diagnostic Needs':\n",
41+
" return [\"Connect with a Diagnostic Center\", \"Verify with a Doctor\", \"Home Sample Collection\"]\n",
42+
" elif user_scenario == 'Prescription Refill':\n",
43+
" return [\"Order Medication\", \"Get a Prescription\", \"Talk to a Pharmacist\", \"Auto-Refill Subscription\"]\n",
44+
" elif user_scenario == 'Preventive Care':\n",
45+
" return [\"Schedule a Check-up\", \"Health Coach Consultation\", \"Vaccination Booking\"]\n",
46+
" elif user_scenario == 'Post-Treatment Follow-up':\n",
47+
" return [\"Talk to a Doctor\", \"Schedule a Follow-up\", \"Physical Therapy Consultation\"]\n",
48+
" else:\n",
49+
" return [\"Talk to a Doctor\"]\n"
50+
]
51+
},
52+
{
53+
"cell_type": "code",
54+
"execution_count": 5,
55+
"metadata": {},
56+
"outputs": [
57+
{
58+
"name": "stdout",
59+
"output_type": "stream",
60+
"text": [
61+
"['Talk to a Doctor', 'Verify with a Doctor', 'Symptom Checker (AI-based)']\n"
62+
]
63+
}
64+
],
65+
"source": [
66+
"# Example usage\n",
67+
"user_profile = 'Chronic Condition Management'\n",
68+
"user_scenario = 'Patient with Symptoms'\n",
69+
"recommendation = rule_based_recommendation(user_profile, user_scenario)\n",
70+
"print(recommendation)"
71+
]
72+
},
73+
{
74+
"cell_type": "markdown",
75+
"metadata": {},
76+
"source": [
77+
"#### 2. Collaborative Filtering"
78+
]
79+
},
80+
{
81+
"cell_type": "code",
82+
"execution_count": 2,
83+
"metadata": {},
84+
"outputs": [],
85+
"source": [
86+
"import numpy as np\n",
87+
"from sklearn.metrics.pairwise import cosine_similarity"
88+
]
89+
},
90+
{
91+
"cell_type": "code",
92+
"execution_count": null,
93+
"metadata": {},
94+
"outputs": [],
95+
"source": [
96+
"# Example user-item interaction matrix (rows: users, columns: options)\n",
97+
"interaction_matrix = np.array([\n",
98+
" [1, 1, 0, 0, 0, 0, 0, 0, 0], # User 1\n",
99+
" [0, 1, 1, 0, 0, 0, 0, 0, 0], # User 2\n",
100+
" [0, 0, 1, 1, 0, 0, 0, 0, 0], # User 3\n",
101+
" [0, 0, 0, 1, 1, 1, 0, 0, 0], # User 4\n",
102+
" [0, 0, 0, 0, 1, 1, 1, 0, 0], # User 5\n",
103+
" [0, 0, 0, 0, 0, 1, 1, 1, 0], # User 6\n",
104+
"])\n",
105+
"\n",
106+
"# Calculate similarity between users\n",
107+
"user_similarity = cosine_similarity(interaction_matrix)"
108+
]
109+
},
110+
{
111+
"cell_type": "code",
112+
"execution_count": null,
113+
"metadata": {},
114+
"outputs": [],
115+
"source": [
116+
"# Recommend based on the most similar user's interactions\n",
117+
"def collaborative_filtering_recommendation(user_index, interaction_matrix, user_similarity):\n",
118+
" similar_user_index = np.argmax(user_similarity[user_index])\n",
119+
" recommendations = np.where(interaction_matrix[similar_user_index] == 1)[0]\n",
120+
" return recommendations"
121+
]
122+
},
123+
{
124+
"cell_type": "code",
125+
"execution_count": null,
126+
"metadata": {},
127+
"outputs": [],
128+
"source": [
129+
"# Example usage\n",
130+
"user_index = 0 # User 1\n",
131+
"recommendations = collaborative_filtering_recommendation(user_index, interaction_matrix, user_similarity)\n",
132+
"print(recommendations) # Output the indices of the recommended options"
133+
]
134+
},
135+
{
136+
"cell_type": "markdown",
137+
"metadata": {},
138+
"source": [
139+
"#### 3. Content-Based Filtering"
140+
]
141+
},
142+
{
143+
"cell_type": "code",
144+
"execution_count": 3,
145+
"metadata": {},
146+
"outputs": [],
147+
"source": [
148+
"from sklearn.feature_extraction.text import TfidfVectorizer\n",
149+
"\n",
150+
"# Example option descriptions\n",
151+
"options = [\n",
152+
" \"Talk to a Doctor for immediate consultation\",\n",
153+
" \"Verify with a Doctor for second opinion\",\n",
154+
" \"Use Symptom Checker to self-diagnose\",\n",
155+
" \"Get a Prescription for chronic condition\",\n",
156+
" \"Order Medication online\",\n",
157+
" \"Talk to a Pharmacist for medication advice\",\n",
158+
" \"Health Coach Consultation for chronic condition management\",\n",
159+
" \"Medication Information for new prescriptions\",\n",
160+
" \"Medication Interaction Checker\",\n",
161+
" \"Connect with a Diagnostic Center for tests\",\n",
162+
" \"Home Sample Collection for diagnostics\",\n",
163+
" \"Book Lab Tests Online\",\n",
164+
" \"Schedule a Check-up for preventive care\",\n",
165+
" \"Health Screening Packages for preventive care\",\n",
166+
" \"Vaccination Booking for preventive care\",\n",
167+
" \"Schedule a Follow-up for post-treatment\",\n",
168+
" \"Physical Therapy Consultation for recovery\",\n",
169+
" \"Remote Monitoring Services for follow-up\",\n",
170+
" \"Talk to a Therapist for mental health support\",\n",
171+
" \"Join a Support Group for mental health\",\n",
172+
" \"Mental Health Self-assessment (AI-based)\",\n",
173+
" \"Meditation and Mindfulness Resources\"\n",
174+
"]\n",
175+
"\n",
176+
"# User profile description\n",
177+
"user_profile_description = \"Patient with chronic condition needing regular medication and follow-ups\"\n"
178+
]
179+
},
180+
{
181+
"cell_type": "code",
182+
"execution_count": null,
183+
"metadata": {},
184+
"outputs": [],
185+
"source": [
186+
"# Vectorize the descriptions\n",
187+
"vectorizer = TfidfVectorizer()\n",
188+
"option_vectors = vectorizer.fit_transform(options)\n",
189+
"user_vector = vectorizer.transform([user_profile_description])\n",
190+
"\n",
191+
"similarity = cosine_similarity(user_vector, option_vectors)"
192+
]
193+
},
194+
{
195+
"cell_type": "code",
196+
"execution_count": null,
197+
"metadata": {},
198+
"outputs": [],
199+
"source": [
200+
"# Recommend based on the highest similarity scores\n",
201+
"def content_based_recommendation(similarity, options):\n",
202+
" recommendations = np.argsort(similarity[0])[::-1]\n",
203+
" return [options[i] for i in recommendations[:5]]"
204+
]
205+
},
206+
{
207+
"cell_type": "code",
208+
"execution_count": null,
209+
"metadata": {},
210+
"outputs": [],
211+
"source": [
212+
"# Example usage\n",
213+
"recommendations = content_based_recommendation(similarity, options)\n",
214+
"print(recommendations)"
215+
]
216+
},
217+
{
218+
"cell_type": "markdown",
219+
"metadata": {},
220+
"source": [
221+
"#### 4. Machine Learning Model"
222+
]
223+
},
224+
{
225+
"cell_type": "code",
226+
"execution_count": null,
227+
"metadata": {},
228+
"outputs": [],
229+
"source": [
230+
"# using a decision tree classifier\n",
231+
"from sklearn.tree import DecisionTreeClassifier\n",
232+
"from sklearn.model_selection import train_test_split"
233+
]
234+
},
235+
{
236+
"cell_type": "code",
237+
"execution_count": null,
238+
"metadata": {},
239+
"outputs": [],
240+
"source": [
241+
"# Example dataset (features: user profile data, labels: recommended options)\n",
242+
"# This is a simplified example; in practice, you would have a more complex dataset\n",
243+
"X = np.array([\n",
244+
" [25, 1, 0, 1], # User 1: age, chronic condition, acute symptoms, preventive care\n",
245+
" [45, 1, 1, 0], # User 2\n",
246+
" [60, 0, 0, 1], # User 3\n",
247+
" [35, 1, 0, 1], # User 4\n",
248+
" [50, 0, 1, 0], # User 5\n",
249+
"])\n",
250+
"y = np.array([\n",
251+
" [0, 1, 1, 0], # Recommended options for User 1\n",
252+
" [1, 1, 0, 1], # Recommended options for User 2\n",
253+
" [0, 0, 1, 1], # Recommended options for User 3\n",
254+
" [1, 1, 0, 0], # Recommended options for User 4\n",
255+
" [0, 0, 1, 1], # Recommended options for User 5\n",
256+
"])"
257+
]
258+
},
259+
{
260+
"cell_type": "code",
261+
"execution_count": null,
262+
"metadata": {},
263+
"outputs": [],
264+
"source": [
265+
"# Split the data into training and testing sets\n",
266+
"X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)"
267+
]
268+
},
269+
{
270+
"cell_type": "code",
271+
"execution_count": null,
272+
"metadata": {},
273+
"outputs": [],
274+
"source": [
275+
"# Train the decision tree classifier\n",
276+
"clf = DecisionTreeClassifier()\n",
277+
"clf.fit(X_train, y_train)"
278+
]
279+
},
280+
{
281+
"cell_type": "code",
282+
"execution_count": null,
283+
"metadata": {},
284+
"outputs": [],
285+
"source": [
286+
"# Predict recommendations for a new user\n",
287+
"new_user = np.array([[40, 1, 1, 0]]) # New user profile\n",
288+
"predictions = clf.predict(new_user)\n",
289+
"print(predictions)"
290+
]
291+
},
292+
{
293+
"cell_type": "code",
294+
"execution_count": null,
295+
"metadata": {},
296+
"outputs": [],
297+
"source": []
298+
},
299+
{
300+
"cell_type": "markdown",
301+
"metadata": {},
302+
"source": []
303+
}
304+
],
305+
"metadata": {
306+
"kernelspec": {
307+
"display_name": "Python 3",
308+
"language": "python",
309+
"name": "python3"
310+
},
311+
"language_info": {
312+
"codemirror_mode": {
313+
"name": "ipython",
314+
"version": 3
315+
},
316+
"file_extension": ".py",
317+
"mimetype": "text/x-python",
318+
"name": "python",
319+
"nbconvert_exporter": "python",
320+
"pygments_lexer": "ipython3",
321+
"version": "3.11.9"
322+
}
323+
},
324+
"nbformat": 4,
325+
"nbformat_minor": 2
326+
}

0 commit comments

Comments
 (0)