Removed old files and added MSRParaphrase parser

basic-testing/parse_file.py

@@ -0,0 +1,6 @@
+import pandas as pd
+
+def load_msr_data(file_path):
+    """Load the MSR Paraphrase Corpus from a TSV file."""
+    df = pd.read_csv("../data/processed/msr_paraphrase_train.txt", sep='\t', quoting=3)
+    return df

basic-testing/parse_tree.py

@@ -0,0 +1,29 @@
+import spacy
+from spacy import displacy
+
+# Load the model
+nlp = spacy.load("en_core_web_sm")
+
+def extract_parse_tree(text):
+    """Extract basic parse tree information"""
+    doc = nlp(text)
+    
+    print(f"Sentence: {text}")
+    print("\nDependency Parse Tree:")
+    print("-" * 50)
+    
+    for token in doc:
+        print(f"{token.text:<12} {token.dep_:<12} {token.head.text:<12} {[child.text for child in token.children]}")
+    
+    return doc
+
+# Test with some sentences
+test_sentences = [
+    "The cat sat on the mat.",
+    "A quick brown fox jumps over the lazy dog.",
+    "She gave him the book yesterday."
+]
+
+for sentence in test_sentences:
+    doc = extract_parse_tree(sentence)
+    print("\n" + "="*60 + "\n")