Merge pull request #36 from software-students-fall2023/rqn

Rqn

machine-learning-client/machine_learning_client.py

@@ -3,15 +3,15 @@
 to text transcription and analysis of audio transcription
 """
 
-import sys
-import pyaudio
-import pymongo
-import pyaudio
+
 import os
+import pyaudio
+
+
 from pymongo import MongoClient
 import speech_recognition as sr
 from flask_cors import CORS
-from flask import Flask, request, jsonify, send_from_directory
+from flask import Flask, request, jsonify
 from pydub import AudioSegment
 
 app = Flask(__name__)
@@ -23,6 +23,7 @@
 db = client["ml_databse"]
 collection = db["transcription"]
 
+
 app.config["UPLOAD_FOLDER"] = "uploads"
 os.makedirs(app.config["UPLOAD_FOLDER"], exist_ok=True)
 PROJECT_ROOT = os.path.abspath(os.path.join(os.path.dirname(__file__), ".."))
@@ -39,7 +40,7 @@ def add_transcription_mongo(transcription, grade_report):
         result = collection.insert_one(data)
         print(f"Transcription saved to MongoDB with ID: {result.inserted_id}")
 
-    except Exception as e:
+    except Exception as e:  # pylint: disable=broad-exception-caught
         print(f"Error saving transcription to MongoDB: {e}")
 
 
@@ -61,22 +62,21 @@ def audio_to_text(audio_file_string):
     return transcription
 
 
-def grade_transcription(transcription_text):
+def grade_transcription(
+    transcription_text,
+):  # pylint: disable=too-many-branches,too-many-statements
     """
-    Function to generate a page giving a break down and grade of an audio transcript someone had just recorded
+    Function to generate a page giving a break down and grade of an audio transcript someone had just recorded # pylint: disable=line-too-long
     """
 
     grade = 0
     filler_words = 0
     buzz_words = 0
-
-    """filler_words += my_transcript.find()"""
     filler_words += transcription_text.lower().count("uh")
     filler_words += transcription_text.lower().count("um")
     filler_words += transcription_text.lower().count("ah")
     filler_words += transcription_text.lower().count("like")
     filler_words += transcription_text.lower().count("er")
-
     buzz_words += transcription_text.lower().count("education")
     buzz_words += transcription_text.lower().count("major")
     buzz_words += transcription_text.lower().count("college")
@@ -91,59 +91,53 @@ def grade_transcription(transcription_text):
     buzz_words += transcription_text.lower().count("develop")
     buzz_words += transcription_text.lower().count("fulfill")
     buzz_words += transcription_text.lower().count("refine")
-
     print("this value of filler word: ", filler_words)
     print("this value of buzz word: ", buzz_words)
-
     fw_breakdown = ""
     bz_breakdown = ""
     grade_analysis = ""
 
     if buzz_words == 0:
-        bz_breakdown = "You did not use any buzz words. When answering this question, try to talk about your education, work experiences, major, or any jobs you had."
+        bz_breakdown = "You did not use any buzz words. When answering this question, try to talk about your education, work experiences, major, or any jobs you had."  # pylint: disable=line-too-long
     elif 0 < buzz_words <= 5:
-        bz_breakdown = f"You used {buzz_words} buzz words. A decent answer, but you can improve. Try to find more things to say about yourself professionally."
+        bz_breakdown = f"You used {buzz_words} buzz words. A decent answer, but you can improve. Try to find more things to say about yourself professionally."  # pylint: disable=line-too-long
     else:
-        bz_breakdown = f"You used {buzz_words} buzz words. The topics of your answer are acceptable. Make sure to keep in mind your wording and topics."
-
+        bz_breakdown = f"You used {buzz_words} buzz words. The topics of your answer are acceptable. Make sure to keep in mind your wording and topics."  # pylint: disable=line-too-long
     if filler_words == 0:
-        fw_breakdown = "You did not use any filler words. Or there was a problem with the audio transcript. Either way, remember to talk confidently and at a good pace."
+        fw_breakdown = "You did not use any filler words. Or there was a problem with the audio transcript. Either way, remember to talk confidently and at a good pace."  # pylint: disable=line-too-long
     elif 0 < filler_words <= 5:
-        fw_breakdown = f"You used {filler_words} filler words. From here, you just need to practice your answer until it comes out naturally. Make sure to keep relaxed."
+        fw_breakdown = f"You used {filler_words} filler words. From here, you just need to practice your answer until it comes out naturally. Make sure to keep relaxed."  # pylint: disable=line-too-long
     else:
-        fw_breakdown = f"You used {filler_words} filler words. When giving your answer, try speaking slower and more clearly. Don't confuse yourself by thinking too far ahead."
-
+        fw_breakdown = f"You used {filler_words} filler words. When giving your answer, try speaking slower and more clearly. Don't confuse yourself by thinking too far ahead."  # pylint: disable=line-too-long
     grade = (buzz_words * 3) - filler_words
     print(grade)
     if grade > 20:
         grade = 20
     elif grade < 0:
         grade = 0
     if grade == 0:
-        grade_analysis = f"Your grade is {grade}/20. You should rethink your answer to be more focused and clearly thought out."
+        grade_analysis = f"Your grade is {grade}/20. You should rethink your answer to be more focused and clearly thought out."  # pylint: disable=line-too-long
     elif 0 < grade <= 5:
-        grade_analysis = f"Your grade is {grade}/20. Refine your answer by reflecting on your education, work experience, and relevant info."
+        grade_analysis = f"Your grade is {grade}/20. Refine your answer by reflecting on your education, work experience, and relevant info."  # pylint: disable=line-too-long
     elif 5 < grade <= 10:
-        grade_analysis = f"Your grade is {grade}/20. You're answer fulfills some of the necessary buzz words. If you have any more relevant data or ways to improve your speech, do so."
+        grade_analysis = f"Your grade is {grade}/20. You're answer fulfills some of the necessary buzz words. If you have any more relevant data or ways to improve your speech, do so."  # pylint: disable=line-too-long
     elif 10 < grade <= 15:
-        grade_analysis = f"Your grade is {grade}/20. You gave a very good response. Everything beyond this is fine tuning your response to the interviewer."
+        grade_analysis = f"Your grade is {grade}/20. You gave a very good response. Everything beyond this is fine tuning your response to the interviewer."  # pylint: disable=line-too-long
     else:
-        grade_analysis = f"Your grade is {grade}/20. This should be your go to answer, but it all depends on the interviewer. This answer should could out naturally and be your basis."
-
+        grade_analysis = f"Your grade is {grade}/20. This should be your go to answer, but it all depends on the interviewer. This answer should could out naturally and be your basis."  # pylint: disable=line-too-long
     grade_report = {
         "filler_words": fw_breakdown,
         "buzz_words": bz_breakdown,
         "grade_analysis": grade_analysis,
     }
-
     print(fw_breakdown)
     print(bz_breakdown)
     print(grade_analysis)
     return grade_report
 
 
 @app.route("/analyzeAudio", methods=["POST"])
-def analyze_Audios():
+def analyze_Audios():  # pylint: disable=invalid-name
     """
     Endpoint to receive and analyze audio file
     """
@@ -185,16 +179,16 @@ def analyze_Audios():
         transcription = audio_to_text(true_audio_path_str)
         print(transcription)
         print("calling grade to text method")
-        gradedTranscription = grade_transcription(transcription)
-        add_transcription_mongo(transcription, gradedTranscription)
+        graded_transcription = grade_transcription(transcription)
+        add_transcription_mongo(transcription, graded_transcription)
 
         print("we did it baby")
         return (
             jsonify({"status": "success", "message": "Audio analysis completed"}),
             200,
         )
 
-    except Exception as e:
+    except Exception as e:  # pylint: disable=broad-exception-caught
         return (
             jsonify({"status": "error", "message": f"An error occurred: {str(e)}"}),
             500,

machine-learning-client/tests/ml_tests.py

@@ -1,69 +1,92 @@
 """
 tests for machine-learning-client
 """
-import machine_learning_client as ML
 import os
+import machine_learning_client as ML  # pylint: disable=import-error
 import pytest
-from flask import Flask
-from flask_cors import CORS
-from flask import Flask, request, jsonify
-from flask.testing import FlaskClient
-from flask_cors import CORS
-from pytest_flask import fixtures
-from machine_learning_client import audio_to_text, grade_transcription, add_transcription_mongo
+
+
 # Mocking dependencies and functions
 @pytest.fixture
 def mock_dependencies(monkeypatch):
-    monkeypatch.setattr("machine_learning_client.audio_to_text", lambda *args, **kwargs: "mocked_transcription")
-    monkeypatch.setattr("machine_learning_client.grade_transcription", lambda *args, **kwargs: "mocked_grade")
-    monkeypatch.setattr("machine_learning_client.add_transcription_mongo", lambda *args, **kwargs: None)
+    """Setup Mock"""
+    monkeypatch.setattr(
+        "machine_learning_client.audio_to_text",
+        lambda *args, **kwargs: "mocked_transcription",
+    )
+    monkeypatch.setattr(
+        "machine_learning_client.grade_transcription",
+        lambda *args, **kwargs: "mocked_grade",
+    )
+    monkeypatch.setattr(
+        "machine_learning_client.add_transcription_mongo", lambda *args, **kwargs: None
+    )
+
 
 # Create a fixture for the Flask application with CORS enabled
 @pytest.fixture
 def client():
-    with ML.app.test_client() as client:
+    """Create a fixture for the Flask application with CORS enabled"""
+    with ML.app.test_client() as client:  # pylint: disable=redefined-outer-name
         yield client
 
+
 # Test the route handler with a valid audio file
-def test_analyze_audios_valid_audio(client):
+def test_analyze_audios_valid_audio(client):  # pylint: disable=redefined-outer-name
+    """Test the route handler with a valid audio file"""
     audio_file_path = os.path.join(os.path.dirname(__file__), "test_audio.webm")
     print(audio_file_path)
     with open(audio_file_path, "rb") as audio_file:
-        response = client.post("/analyzeAudio", data={"audio": (audio_file, "test_audio.webm")})
+        response = client.post(
+            "/analyzeAudio", data={"audio": (audio_file, "test_audio.webm")}
+        )
 
     assert response.status_code == 200
     assert response.json == {"status": "success", "message": "Audio analysis completed"}
 
+
 # Test the route handler without including an audio file
-def test_analyze_audios_no_audio_file(client):
+def test_analyze_audios_no_audio_file(client):  # pylint: disable=redefined-outer-name
+    """Test the route handler without including an audio file"""
     response = client.post("/analyzeAudio")
 
     assert response.status_code == 400
     assert response.json == {"status": "error", "message": "No audio file provided"}
 
+
 # Test the route handler with an exception during audio processing
-def test_analyze_audios_exception(client, monkeypatch):
-    monkeypatch.setattr("machine_learning_client.audio_to_text", lambda *args, **kwargs: Exception("Mocked exception"))
+def test_analyze_audios_exception(
+    client, monkeypatch
+):  # pylint: disable=redefined-outer-name
+    """Test the route handler with an exception during audio processing"""
+    monkeypatch.setattr(
+        "machine_learning_client.audio_to_text",
+        lambda *args, **kwargs: Exception("Mocked exception"),
+    )
 
     audio_file_path = os.path.join(os.path.dirname(__file__), "test_audio.webm")
 
     with open(audio_file_path, "rb") as audio_file:
-        response = client.post("/analyzeAudio", data={"audio": (audio_file, "test_audio.webm")})
+        response = client.post(
+            "/analyzeAudio", data={"audio": (audio_file, "test_audio.webm")}
+        )
 
     assert response.status_code == 500
     assert response.json["status"] == "error"
 
     # Asserting that the error message starts with "An error occurred:"
     assert response.json["message"].startswith("An error occurred:")
 
+
 class Tests:
     """Tests class for ml_tests.py"""
+
     def test_audio_text_conversion(self):
         """testing audio_to_text function in ML with valid audiofile as input"""
-        PROJECT_ROOT = os.path.abspath(os.path.join(os.path.dirname(__file__), ".."))
+        project_root = os.path.abspath(os.path.join(os.path.dirname(__file__), ".."))
         tests_path = "tests"
         file_name = "richard.aiff"
-        file_path = os.path.join(PROJECT_ROOT, tests_path, file_name)
+        file_path = os.path.join(project_root, tests_path, file_name)
         print(file_path)
         actual = ML.audio_to_text(file_path)
         assert isinstance(
@@ -72,45 +95,51 @@ def test_audio_text_conversion(self):
         assert (
             actual.lower() == "my name is richard"
         ), f"Expected the converted audio to be 'my name is richard'. Instead it returned {actual}"
-
-
-
 
     def test_grade_transcription_good(self):
-        """testing grade_transcription function in ML with a recording of all filler && buzz words"""
-        PROJECT_ROOT = os.path.abspath(os.path.join(os.path.dirname(__file__), ".."))
+        """testing grade_transcription function in ML with a recording of all filler && buzz words"""  # pylint: disable=line-too-long
+        project_root = os.path.abspath(os.path.join(os.path.dirname(__file__), ".."))
         tests_path = "tests"
         file_name = "filler.aiff"
-        file_path = os.path.join(PROJECT_ROOT, tests_path, file_name)
+        file_path = os.path.join(project_root, tests_path, file_name)
         actual = ML.grade_transcription(ML.audio_to_text(file_path))
-        assert isinstance(actual, dict), f"Expected grade_transcription to return a dict. Instead it returned a {actual}"
-        assert (actual == {"filler_words": "You used 7 filler words. When giving your answer, try speaking slower and more clearly. Don't confuse yourself by thinking too far ahead.",
-        "buzz_words": "You used 14 buzz words. The topics of your answer are acceptable. Make sure to ",
-        "grade_analysis": "Your grade is 20/20. This should be your go to answer, but it all depends on the interviewer. This answer should could out naturally and be your basis."}
-                ), f"Expected a 20 grade report. Instead it returned {actual}"
-
+        assert isinstance(
+            actual, dict
+        ), f"Expected grade_transcription to return a dict. Instead it returned a {actual}"
+        assert actual == {
+            "filler_words": "You used 7 filler words. When giving your answer, try speaking slower and more clearly. Don't confuse yourself by thinking too far ahead.",  # pylint: disable=line-too-long
+            "buzz_words": "You used 14 buzz words. The topics of your answer are acceptable. Make sure to keep in mind your wording and topics.",  # pylint: disable=line-too-long
+            "grade_analysis": "Your grade is 20/20. This should be your go to answer, but it all depends on the interviewer. This answer should could out naturally and be your basis.",  # pylint: disable=line-too-long
+        }, f"Expected a 20 grade report. Instead it returned {actual}"
+
     def test_grade_transcription_gt5(self):
         """testing grade_transcription function in ML with a recording of many filler/buzz words"""
-        PROJECT_ROOT = os.path.abspath(os.path.join(os.path.dirname(__file__), ".."))
+        project_root = os.path.abspath(os.path.join(os.path.dirname(__file__), ".."))
         tests_path = "tests"
         file_name = "gt5.aiff"
-        file_path = os.path.join(PROJECT_ROOT, tests_path, file_name)
+        file_path = os.path.join(project_root, tests_path, file_name)
         actual = ML.grade_transcription(ML.audio_to_text(file_path))
-        assert isinstance(actual, dict), f"Expected grade_transcription to return a dict. Instead it returned a {actual}"
-        assert (actual == {"filler_words": "You did not use any filler words. Or there was a problem with the audio transcript. Either way, remember to talk confidently and at a good pace.",
-        "buzz_words": "You did not use any buzz words. When answering this question, try to talk about your education, work experiences, major, or any jobs you had.",
-        "grade_analysis": "Your grade is 0/20. You should rethink your answer to be more focused and clearly thought out."}
-                ), f"Expected a 0 grade report. Instead it returned {actual}"
-
+        assert isinstance(
+            actual, dict
+        ), f"Expected grade_transcription to return a dict. Instead it returned a {actual}"
+        assert actual == {
+            "filler_words": "You did not use any filler words. Or there was a problem with the audio transcript. Either way, remember to talk confidently and at a good pace.",  # pylint: disable=line-too-long
+            "buzz_words": "You did not use any buzz words. When answering this question, try to talk about your education, work experiences, major, or any jobs you had.",  # pylint: disable=line-too-long
+            "grade_analysis": "Your grade is 0/20. You should rethink your answer to be more focused and clearly thought out.",  # pylint: disable=line-too-long
+        }, f"Expected a 0 grade report. Instead it returned {actual}"
+
     def test_grade_transcription_5(self):
         """testing grade_transcription function in ML with a recording of 5 filler/buzz"""
-        PROJECT_ROOT = os.path.abspath(os.path.join(os.path.dirname(__file__), ".."))
+        project_root = os.path.abspath(os.path.join(os.path.dirname(__file__), ".."))
         tests_path = "tests"
         file_name = "5.aiff"
-        file_path = os.path.join(PROJECT_ROOT, tests_path, file_name)
+        file_path = os.path.join(project_root, tests_path, file_name)
         actual = ML.grade_transcription(ML.audio_to_text(file_path))
-        assert isinstance(actual, dict), f"Expected grade_transcription to return a dict. Instead it returned a {actual}"
-        assert (actual == {"filler_words": "You used 16 filler words. When giving your answer, try speaking slower and more clearly. Don't confuse yourself by thinking too far ahead.",
-        "buzz_words": "You did not use any buzz words. When answering this question, try to talk about your education, work experiences, major, or any jobs you had.",
-        "grade_analysis": "Your grade is 0/20. You should rethink your answer to be more focused and clearly thought out."}
-                ), f"Expected a 0 grade report. Instead it returned {actual}"
+        assert isinstance(
+            actual, dict
+        ), f"Expected grade_transcription to return a dict. Instead it returned a {actual}"
+        assert actual == {
+            "filler_words": "You used 16 filler words. When giving your answer, try speaking slower and more clearly. Don't confuse yourself by thinking too far ahead.",  # pylint: disable=line-too-long
+            "buzz_words": "You did not use any buzz words. When answering this question, try to talk about your education, work experiences, major, or any jobs you had.",  # pylint: disable=line-too-long
+            "grade_analysis": "Your grade is 0/20. You should rethink your answer to be more focused and clearly thought out.",  # pylint: disable=line-too-long
+        }, f"Expected a 0 grade report. Instead it returned {actual}"

web-app/app.py

@@ -59,9 +59,7 @@ def analyze_data():
             result = response.json()
             return jsonify(result)
         return (
-            jsonify(
-                {"error": "Failed to send and process audio. Please try again."}
-            ),
+            jsonify({"error": "Failed to send and process audio. Please try again."}),
             500,
         )