first draft

.gitignore

@@ -0,0 +1,165 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+.idea/
+.ipynb_checkpoints
+config
+notebooks/.ipynb_checkpoints
+.DS_Store
+

README.md

@@ -11,3 +11,9 @@ license: mit
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+
+### TODO List
+[ ] Consent form
+[ ] Instructions
+[ ] Add proceed button after prolific id
+[ ] Make sure each question has at least 10 responses

app.py

@@ -1,96 +1,159 @@
+from db.schema import Feedback, Response
+from db.crud import ingest
 import pandas as pd
 import streamlit as st
-import sqlite3
-
-# Database setup
-DB_FILE = "feedback.db"
-
-def init_db():
-    # Connect to SQLite database
-    conn = sqlite3.connect(DB_FILE)
-    cursor = conn.cursor()
-
-    # Create a table for storing feedback if not exists
-    cursor.execute("""
-        CREATE TABLE IF NOT EXISTS feedback (
-            id INTEGER PRIMARY KEY AUTOINCREMENT,
-            question TEXT,
-            selected_answer TEXT,
-            rating INTEGER,
-            feedback_text TEXT
-        )
-    """)
-    conn.commit()
-    conn.close()
-
-def store_feedback(question, rating, feedback_text):
-    conn = sqlite3.connect(DB_FILE)
-    cursor = conn.cursor()
-    cursor.execute("""
-        INSERT INTO feedback (question, rating, feedback_text)
-        VALUES (?, ?, ?)
-    """, (question, rating, feedback_text))
-    conn.commit()
-    conn.close()
-
-# Initialize database
-init_db()
+from datetime import datetime
+
 
 # Load Q&A data
 @st.cache_data
 def load_data():
-    return pd.read_csv("dummy_qa_data.csv")
+    return pd.read_csv("dummy_qa_data.csv")[:3]
+
+
+# Function to validate Prolific ID (customize this based on your format requirements)
+def validate_prolific_id(prolific_id: str) -> bool:
+    return bool(prolific_id.strip())  # Example: Check non-empty
 
-data = load_data()
+    # Function to reset the survey
 
-# Session state for question navigation
-if "current_index" not in st.session_state:
+
+def reset_survey():
+    st.session_state.prolific_id = None
     st.session_state.current_index = 0
+    st.session_state.responses = []
+    st.session_state.completed = False
+
+
+def initialization():
+    """Initialize session state variables."""
+    if "current_index" not in st.session_state:
+        st.session_state.current_index = 0
+    if "prolific_id" not in st.session_state:
+        st.session_state.prolific_id = None
+    if "responses" not in st.session_state:
+        st.session_state.responses = []
+    if "completed" not in st.session_state:
+        st.session_state.completed = False
+
+
+def prolific_id_screen():
+    """Display the Prolific ID entry screen."""
+    st.title("Welcome to the Feedback Survey")
+    prolific_id_input = st.text_input("Enter your Prolific ID and press ENTER:")
+
+    if prolific_id_input:
+        if validate_prolific_id(prolific_id_input):
+            st.session_state.prolific_id = prolific_id_input
+            st.success("Prolific ID recorded! Now, proceed with the questions.")
+            st.experimental_rerun()
+        else:
+            st.warning("Invalid Prolific ID. Please check and try again.")
 
-# Current question index
-current_index = st.session_state.current_index
 
-# Display question and options
-if 0 <= current_index < len(data):
+def questions_screen(data):
+    """Display the questions screen."""
+    current_index = st.session_state.current_index
+
+    # Display question and answer
     question = data.loc[current_index, "Question"]
-    # answers = eval(data.loc[current_index, "Generated Answer"])  # Convert string to list of tuples
+    generated_answer = data.loc[current_index, "Generated Answer"]
 
-    st.subheader(f"Question {current_index + 1}: {question}")
+    st.subheader(f"Question {current_index + 1}")
+    st.markdown(f"***{question}***")
     st.subheader("Generated Answer:")
-    st.write(data.loc[current_index, "Generated Answer"])
-    # selected_answer = st.radio("Choose the best answer:", options=[ans[0] for ans in answers])
-
-    # Rating
-    rating = st.slider("Rate the answer (1 = Worst, 5 = Best)", 1, 5, value=3)
+    st.write(generated_answer)
+
+    # Prefill responses if they exist
+    previous_rating = (
+        st.session_state.responses[current_index].ans
+        if len(st.session_state.responses) > current_index
+        else 0
+    )
+    previous_feedback = (
+        st.session_state.responses[current_index].feedback_text
+        if len(st.session_state.responses) > current_index
+        else ""
+    )
+
+    # Rating slider
+    rating = st.slider("Rate the answer (1 = Worst, 5 = Best)", 1, 5, value=previous_rating,
+                       key=f"rating_{current_index}")
 
     # Free-text feedback
-    feedback_text = st.text_area("Any additional feedback?")
+    feedback_text = st.text_area("Any additional feedback?", value=previous_feedback, key=f"feedback_{current_index}")
+
+    # Store or update the response
+    response = Response(q_id=f"q{current_index + 1}", ans=rating, feedback_text=feedback_text)
+    if len(st.session_state.responses) > current_index:
+        st.session_state.responses[current_index] = response
+    else:
+        st.session_state.responses.append(response)
 
     # Navigation buttons
+    navigation_buttons(data, rating, feedback_text)
+
+
+def navigation_buttons(data, rating, feedback_text):
+    """Display navigation buttons."""
+    current_index = st.session_state.current_index
+
     col1, col2, col3 = st.columns([1, 1, 2])
 
-    with col1:
+    with col1:  # Back button
         if st.button("Back") and current_index > 0:
             st.session_state.current_index -= 1
             st.experimental_rerun()
 
-    with col2:
+    with col2:  # Next button
         if st.button("Next"):
-            # Store feedback for the current question
-            store_feedback(question, rating, feedback_text)
-
-            if current_index < len(data) - 1:
-                st.session_state.current_index += 1
-                # st.experimental_rerun()
+            if not rating:
+                st.warning("Please provide a rating before proceeding.")
             else:
-                st.success("You have completed all questions!")
-                st.stop()
-else:
-    st.write("No more questions available!")
-
-# View results for debugging (optional)
-if st.checkbox("Show Feedback Database (Admin Use)"):
-    conn = sqlite3.connect(DB_FILE)
-    df = pd.read_sql_query("SELECT * FROM feedback", conn)
-    st.dataframe(df)
-    conn.close()
+                if current_index < len(data) - 1:
+                    st.session_state.current_index += 1
+                    st.experimental_rerun()
+                else:
+                    feedback = Feedback(
+                        id=current_index + 1,
+                        user_id=st.session_state.prolific_id,
+                        time_stamp=datetime.now(),
+                        responses=st.session_state.responses,
+                    )
+                    try:
+                        ingest(feedback)
+                        st.session_state.completed = True
+                        st.experimental_rerun()
+                    except Exception as e:
+                        st.error(f"An error occurred while submitting feedback: {e}")
+
+
+def reset_survey():
+    """Reset the survey state to start over."""
+    st.session_state.prolific_id = None
+    st.session_state.current_index = 0
+    st.session_state.responses = []
+    st.session_state.completed = False
+
+
+def ui():
+    """Main function to control the survey flow."""
+    data = load_data()
+    initialization()
+
+    if st.session_state.completed:
+        st.title("Survey Completed")
+        st.success("You have completed all questions and your answers have been recorded.")
+        if st.button("Retake Survey"):
+            reset_survey()
+            st.experimental_rerun()
+        return
+
+    if st.session_state.prolific_id is None:
+        prolific_id_screen()
+    else:
+        questions_screen(data)
+
+
+if __name__ == "__main__":
+    ui()

db/crud.py

@@ -0,0 +1,101 @@
+from datetime import datetime
+
+from db.schema import Feedback
+from db.setup import db_setup
+
+
+# Create operation (Ingest data into Firebase with unique user_id check)
+def ingest(data: Feedback):
+    ref = db_setup()  # Ensure Firebase is initialized
+
+    # Check if the user_id already exists in the feedback data
+    existing_feedback = ref.child('feedback').order_by_child('user_id').equal_to(data.user_id).get()
+
+    # TODO: This should probably change. If the same user has multiple feedbacks, we should allow it. -> change to update
+    if existing_feedback:
+        print(f"Feedback from user '{data.user_id}' already exists. Ingestion aborted.")
+    else:
+        feedback_data = data.dict()  # Convert Pydantic model to a dictionary
+        ref.child('feedback').push(feedback_data)
+        print(f"Feedback data from user '{data.user_id}' pushed to Firebase!")
+
+
+# Read operation (Fetch feedback data from Firebase)
+def read(feedback_id: str):
+    ref = db_setup()
+    feedback_ref = ref.child('feedback').order_by_child('id').equal_to(feedback_id).get()
+
+    if feedback_ref:
+        return feedback_ref
+    else:
+        print("Feedback not found!")
+        return None
+
+
+# Update operation (Update feedback data in Firebase)
+def update(feedback_id: int, updated_data: Feedback):
+    ref = db_setup()
+    feedback_ref = ref.child('feedback').order_by_child('id').equal_to(feedback_id).get()
+
+    if feedback_ref:
+        # Assuming we're updating the first entry found
+        for key in feedback_ref:
+            ref.child('feedback').child(key).update(updated_data.dict())
+        print("Feedback data updated in Firebase!")
+    else:
+        print("Feedback not found to update!")
+
+
+# Delete operation (Remove feedback data from Firebase)
+def delete(feedback_id: int):
+    ref = db_setup()
+    feedback_ref = ref.child('feedback').order_by_child('id').equal_to(feedback_id).get()
+
+    if feedback_ref:
+        # Assuming we're deleting the first entry found
+        for key in feedback_ref:
+            ref.child('feedback').child(key).delete()
+        print("Feedback data deleted from Firebase!")
+    else:
+        print("Feedback not found to delete!")
+
+
+def test():
+    # Create a feedback object
+    feedback_example = Feedback(
+        id=1,
+        user_id="user1234",
+        time_stamp=datetime.now(),
+        responses=[
+            {"q_id": "q1", "ans": 5},
+            {"q_id": "q2", "ans": 3}
+        ]
+    )
+
+    # Create (Ingest)
+    ingest(feedback_example)
+
+    # Read (Fetch)
+    feedback_data = read(1)
+    if feedback_data:
+        print(feedback_data)
+
+    # Update (Modify)
+    updated_feedback = Feedback(
+        id=1,
+        user_id="user123",
+        time_stamp=datetime.now(),
+        responses=[
+            {"q_id": "q1", "ans": 4},  # Updated answer
+            {"q_id": "q2", "ans": 3}
+        ]
+    )
+    update(1, updated_feedback)
+
+    # Delete (Remove)
+    delete(1)
+
+
+# Example usage
+if __name__ == "__main__":
+    test()

db/schema.py

@@ -0,0 +1,22 @@
+from pydantic import BaseModel
+from typing import List, Dict
+from datetime import datetime
+
+
+class Response(BaseModel):
+    q_id: str
+    ans: int
+    feedback_text: str | None = None
+
+
+class Feedback(BaseModel):
+    id: int
+    user_id: str
+    time_stamp: datetime
+    responses: List[Response]
+
+    # Override the method to serialize datetime
+    def dict(self, *args, **kwargs):
+        feedback_data = super().dict(*args, **kwargs)
+        feedback_data['time_stamp'] = self.time_stamp.isoformat()  # Convert datetime to ISO string
+        return feedback_data

db/setup.py

@@ -0,0 +1,41 @@
+import base64
+import json
+import os
+import firebase_admin
+from firebase_admin import db
+
+from dotenv import load_dotenv
+
+load_dotenv()
+databaseURL = os.environ["FIREBASE_DATABASE_URL"]
+
+
+def decode_service_key():
+    encoded_key = os.environ["FIREBASE_CREDENTIALS"]
+    original_service_key = json.loads(base64.b64decode(encoded_key).decode('utf-8'))
+    if original_service_key:
+        return original_service_key
+    return None
+
+
+# Firebase initialization
+def initialize_firebase():
+    try:
+        # Try to initialize Firebase app if not already initialized
+        firebase_admin.get_app()
+    except ValueError:
+        creds_file_name = '.config/user-evaluations-firebase-creds.json'
+        if not (os.path.exists(creds_file_name) and os.path.isdir(creds_file_name)):
+            credentials = decode_service_key()
+            with open(creds_file_name, 'w', encoding='utf-8') as file:
+                json.dump(credentials, file, ensure_ascii=False, indent=4)
+        # If not initialized, initialize the default app
+        cred_obj = firebase_admin.credentials.Certificate(creds_file_name)
+        databaseURL = os.environ["FIREBASE_DATABASE_URL"]
+        firebase_admin.initialize_app(cred_obj, {'databaseURL': databaseURL})
+
+
+def db_setup():
+    initialize_firebase()
+    ref = db.reference('/')
+    return ref

requirements.txt

@@ -1,4 +1,8 @@
 streamlit
 pandas
 openpyxl
-pysqlite3 
+pyrebase
+requests==2.11.1
+python-dotenv
+firebase-admin
+pydantic