Create main.py

main.py

@@ -0,0 +1,129 @@
+import streamlit as st
+import random
+import spacy
+import requests
+from bs4 import BeautifulSoup
+import re
+import spacy
+import language_tool_python
+
+# Initialize LanguageTool
+tool = language_tool_python.LanguageToolPublicAPI('en-US')
+
+# Define the Streamlit app
+st.title("NLP Testing and Scoring App")
+
+# Web scraping and text cleaning
+entity = "Canada"
+prefix = "https://wiki.kidzsearch.com/wiki/"
+page = requests.get(f'{prefix}{entity}')
+res = BeautifulSoup(page.content, 'html.parser')
+
+text = [i.get_text() for i in res.find_all('p')]
+
+cleaned_text = ' '.join(text)
+cleaned_text = re.sub(r'[^a-zA-Z0-9.,]', ' ', cleaned_text)
+paragraphs = [p.strip() for p in re.split(r'\n', cleaned_text) if p.strip()]
+
+# Process text using SpaCy
+nlp = spacy.load("en_core_web_sm")
+doc = nlp(cleaned_text)
+
+sentences = [sent.text for sent in doc.sents]
+
+# Combine sentences into paragraphs
+paragraphs = [f"{sentences[i]} {sentences[i + 1]}" if i + 1 < len(sentences) else sentences[i] for i in range(0, len(sentences), 2)]
+
+class SubjectiveTest:
+
+    def __init__(self, data, noOfQues):
+        self.summary = data
+        self.noOfQues = noOfQues
+        self.nlp = spacy.load("en_core_web_sm")
+
+    def adjust_question_pattern(self, entity_label, topic_placeholder=True):
+        question_patterns = {
+            "PERSON": ["Who is {entity}?", "Tell me about {entity}", "Explain {entity}", "What do you know about {entity}"],
+            "ORG": ["What is {entity}?", "Tell me about {entity}", "Explain {entity}", "What do you know about {entity}"],
+            "GPE": ["Tell me about {entity}", "Explain {entity}", "What do you know about {entity}", "Describe {entity}", "Where is {entity}"],
+            "MONEY": ["How much is {entity}?", "Tell me the value of {entity}", "Explain the amount of {entity}"],
+            "DATE": ["Why was {entity} important?", "Explain what happened on {entity}"],
+            # Add more entity-label to question-pattern mappings as needed
+        }
+
+        if topic_placeholder:
+            for key in question_patterns:
+                question_patterns[key] = [pattern + " {topic}" for pattern in question_patterns[key]]
+
+        return question_patterns.get(entity_label, ["Explain {entity} {topic}"])
+
+    def generate_test(self, topic=None):
+        doc = self.nlp(self.summary)
+        question_answer_dict = dict()
+
+        for sentence in doc.sents:
+            for ent in sentence.ents:
+                entity_label = ent.label_
+                entity_text = ent.text
+                question_patterns = self.adjust_question_pattern(entity_label, topic is not None)
+                for pattern in question_patterns:
+                    question = pattern.format(entity=entity_text, topic=topic)
+                    if entity_label in question_answer_dict:
+                        question_answer_dict[entity_label].append(question)
+                    else:
+                        question_answer_dict[entity_label] = [question]
+
+        questions = []
+
+        for entity_label, entity_questions in question_answer_dict.items():
+            entity_questions = entity_questions[:self.noOfQues]
+            questions.extend(entity_questions)
+
+        return questions
+
+# Example usage
+data = ' '.join(paragraphs)
+noOfQues = 5
+
+subjective_generator = SubjectiveTest(data, noOfQues)
+question_list = subjective_generator.generate_test("")
+questions = []
+for i, question in enumerate(question_list):
+  if "Explain" not in question and len(tool.check(question)) == 0 and grammar_sense(question) == "Make Sense":
+    questions.append(f"Question: {question}")
+
+scores = []
+
+# Now, add a Streamlit UI for input and displaying scores
+st.subheader("Answer the following questions:")
+user_responses = {}
+for i, question in enumerate(questions):
+    response = st.text_area(f"Question {i + 1}", key=f"response_{i}")
+    user_responses[f"response_{i}"] = response
+
+if st.button("Calculate Scores"):
+    for i in questions:
+        res = user_responses[f"response_{i}"]
+        # Simulate the scoring process, replace with your actual scoring logic
+        score = random.randint(0, 100)
+        scores.append(score)
+
+    x = 0
+    new_scores = []
+    for i in scores:
+        if i == 'N/A':
+            scores.pop(x)
+            scores.append(85)
+            x = x + 1
+        else:
+            x = x + 1
+
+    def calculate_average(numbers):
+        if not numbers:
+            return 0  # Return 0 for an empty list to avoid division by zero.
+
+        total = sum(numbers)
+        average = total / len(numbers)
+        return average
+
+    st.subheader(f'Your average score is {calculate_average(scores)}')