From 188a8e58522a9ad0416de5fcb938b3933dee59b7 Mon Sep 17 00:00:00 2001
From: Henry Dowd <henrydowd@outlook.com>
Date: Wed, 8 Oct 2025 14:55:08 +0100
Subject: [PATCH] simple sentance parser and dataset tester program

---
 .gitignore                                   |   2 +
 __init__.py                                  |   0
 __pycache__/parser.cpython-313.pyc           | Bin 0 -> 790 bytes
 main.py                                      |  14 +++++++
 testing/__init__.py                          |   0
 testing/__pycache__/datasets.cpython-313.pyc | Bin 0 -> 1729 bytes
 testing/dataset_testing.py                   |  41 +++++++++++++++++++
 tools/__init__.py                            |   0
 tools/__pycache__/__init__.cpython-313.pyc   | Bin 0 -> 151 bytes
 tools/__pycache__/parser.cpython-313.pyc     | Bin 0 -> 1500 bytes
 tools/parser.py                              |  35 ++++++++++++++++
 11 files changed, 92 insertions(+)
 create mode 100644 .gitignore
 create mode 100644 __init__.py
 create mode 100644 __pycache__/parser.cpython-313.pyc
 create mode 100644 main.py
 create mode 100644 testing/__init__.py
 create mode 100644 testing/__pycache__/datasets.cpython-313.pyc
 create mode 100644 testing/dataset_testing.py
 create mode 100644 tools/__init__.py
 create mode 100644 tools/__pycache__/__init__.cpython-313.pyc
 create mode 100644 tools/__pycache__/parser.cpython-313.pyc
 create mode 100644 tools/parser.py

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..e75ccaa
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,2 @@
+venv
+.vscode
diff --git a/__init__.py b/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/__pycache__/parser.cpython-313.pyc b/__pycache__/parser.cpython-313.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..1693ab5e06143362738843b6b635821b7ffc2619
GIT binary patch
literal 790
zcmZuvzi-n}5I+0ajvMlWKtYHBnYJKBB7`3Tp(<i2h$^T}i5pS1sFrI#NP=TqwkwFI
zh=oclWvEy?(uuVrow^!<Kzc1Ku&@>7AK)Bn3Wby2y}SFq`|kAg`q^w6&<azZoA)??
zuW^zX*$?{HF<1i?RPHW#@Br$3LOHlcK;^HYLTnzdlGEUkM_f_(9v7xrj@p{xcvO2r
zmo&d)>@#B!GI-)y{V(X&VBt5`fJD*e7Lsjni=?VRgF6nBGXOUK2hKP6x`0xLOeJ|x
z1;nI70H&&ln1q=8FZN%pn4d!a;Pw9QQRO^bl@E5DsskK>c-Ju~4o!!rW}U~>E-iIS
zK^!Q$ty^8c<&THbEPWb`D<P>|z7k5xE$aSCE`=#&lIkXAk}^|M@#ZTxiV`EX<ucLr
zT6VyM0GpX$QdeU_6WL5~9bYRFCi~P5sBKV2Ovhm2V5}d%r=loqwA^$$wA`e&*DV{4
zNy~=r`hjE9va5SO^)9+ymK%gxBIM<<Ifci!(Dh(9on2|ZDD@`32}4nO?1OM_r!c%C
z?#kI!X?6Kk_%d7{jZU6lfB3rbW`1LSlSCIPn|I#c-mY#{w`*IqX!d?IF&E7(Mw<Ca
zYrWH2QQL|ZJ5kR5C_6t096PZmK_=g;_HiB*1t$8gZgiPoIlAeISR1Ug0p8I#&Y@#+
urQ?{(7QN{WV;X-d{|vf4!g1UVWKb}bdES23jtXbrOCvqfmr`7Q(Ek&~;j6v?

literal 0
HcmV?d00001

diff --git a/main.py b/main.py
new file mode 100644
index 0000000..3d980d3
--- /dev/null
+++ b/main.py
@@ -0,0 +1,14 @@
+from tools.parser import parse_sentence, extract_dependency_relationships
+
+def main():
+
+    sentence = "The quick brown fox jumps over the lazy dog."
+    doc = parse_sentence(sentence)
+
+    dependencies = extract_dependency_relationships(doc)
+    print("\nDependency relationships:")
+    for dep in dependencies:
+        print(f"{dep['word']} --{dep['dep_type']}--> {dep['head']}")        
+
+if __name__ == "__main__":
+    main()
\ No newline at end of file
diff --git a/testing/__init__.py b/testing/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/testing/__pycache__/datasets.cpython-313.pyc b/testing/__pycache__/datasets.cpython-313.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..26cec17d33018e9e875b1f15978ebb340fc95155
GIT binary patch
literal 1729
zcmah}TTdHD6rR0!ecN4gGl5XZLP%5-jBDH|4N0h~a*0TY5Gz-eV#!+UDRyM<F0%`%
zEmg8ARY9s$Ih7*$k-nvGJd(Hm1iPRXrpZIqzVJpuen8KzFOXi;k@w6wXU_S)nR8}*
zDoFtZBklV$_qhk5KOCbyf-U9rdj_FrNJT1h4=pi-Q5>DU#}d|^xh0<P3QDo7E>=6e
zIgcTgyAJuzAVP`(n^!&8*_Owv3KtRarTpOcw&MUR0Jg7f_oBPsKz1<YRsFC@lnOeM
zh$-I~N{MQ~^@*zM?I24orkDz<QWT<Pq{@lTPJqE-45g%Iwu};No2|9h1#2$izpQlw
zYmdVUsJ;I{?K_7gsbMEhWz~Kj!8wLu-?GbnAtkE=EsR0XFShg{(BEt73E>QB`4U1w
zq@d*|&3T=T3?BnBiZE0x7+N-+)ojhe_5&(oJ)JQKPCv$LX{$*2^};5me36)$Osnor
zBJ#q=!FO5%@eDm|bqS#)YV+#sIWN=kat}K=t2`wCZH%F0r<ywdzp<UJ=$<4>GD$w^
zNwP^!Wu}C26k*G^S2SW_WzDd2iiLF>>lth*nx0kgmp0KdwqoaSo+w#tVm%A1CB?GI
zX2#wm*op|$-%g63snb;Igy*ppf7hI*eAdXsT{#`$D5n=pDwxhT2yL^bI{>9L!3E9E
z8@iRtn?Ol?P!ZyHgy;wf1oc2X5V_N|C4ftD2mL6PGm1Et!#XL&GDa51%!0PAk-Sxm
zX0eSk4sy)KmYvtvW34t@Q)Y>VO=3VTtaST?X;aG+(g)ZMx%C-{3VQ29VraYc?QCW4
zWl(M^Zv`av{wgMZ78AR3`{K>Y{7bRt9s5K;{g)2IBZq_TudDB{tM9es6@?Sz^$4ec
zjLJhRO@7#yvb?(TDU?Plngwi4O-&s;SBrX}L3#bG9%X-Ez8Rw&JNJz;Gi6b2HC2hv
zDCewcu)O!RHC&icsHfm4<x%DR_#J43X66Xo_DSV~JGx;jXP!uTI55|~2+&#O3xg=<
z2#E6^b?m&aGOH+*e{7I!nNy-s>Vy8I?UIShd^9=>OF67%BO&lNAC^U$C$dZ}Q=+16
z7zJp8dnZW9ISTJQLn1q>x0U0zf_hAn*KO({n!b)Hlc(NRou~jebhBVn4!D0rBn-Kv
z*8%X|E*ja*0-hz;z;r5Qi6BonhGAZz(ch5x3JpVxyyBBbUq7mMkM0X&749g|U)`#0
z?FX(_yl?m(MtD7e7@;m)K0xC~etCQ2yMf9lhjO^O-jGLX8x481vUnto?c8{Nt8w|p
z-i4or8aJ2sr3aOT-+BM`Qgx%&{nV=BTD%?@KHx`=z<IyczY}Z>PSyva^}y5tANx<|
zVs){$*ytOt_g<-AS*QmV5BR$PTNft|_{qaixN0;)S9i#BW<NBs%^mrqDqBrdx1Qdr
sMr+niVyFDW$Mvzq?uUEa-olIE?pJkr{ukfEDTlhQy$Pd0k6W$30F36XbN~PV

literal 0
HcmV?d00001

diff --git a/testing/dataset_testing.py b/testing/dataset_testing.py
new file mode 100644
index 0000000..68b8800
--- /dev/null
+++ b/testing/dataset_testing.py
@@ -0,0 +1,41 @@
+import spacy
+from tools import parser
+
+# Load spaCy and dataset
+nlp = spacy.load("en_core_web_sm")
+dataset = parser.load_dataset("glue", "mrpc")
+
+def process_sentence_pair(sentence1, sentence2):
+    """Parse both sentences and extract their dependency structures"""
+    
+    # Parse both sentences
+    doc1 = nlp(sentence1)
+    doc2 = nlp(sentence2)
+    
+    # Extract dependency graphs
+    deps1 = parser.extract_dependency_relationships(doc1)
+    deps2 = parser.extract_dependency_relationships(doc2)
+    
+    return {
+        'sentence1': sentence1,
+        'sentence2': sentence2,
+        'dependencies1': deps1,
+        'dependencies2': deps2,
+        'doc1': doc1,
+        'doc2': doc2
+    }
+
+# Process a few examples from the dataset
+print("Processing MRPC examples...")
+for i in range(3):  # Just do first 3 examples
+    example = dataset['train'][i]
+    result = process_sentence_pair(example['sentence1'], example['sentence2'])
+    
+    print(f"\nExample {i+1}:")
+    print(f"Sentence 1: {result['sentence1']}")
+    print(f"Sentence 2: {result['sentence2']}")
+    print(f"Label: {example['label']} (1=paraphrase, 0=not paraphrase)")
+    
+    print(f"\nDependencies for Sentence 1:")
+    for dep in result['dependencies1'][:5]:  # Show first 5 dependencies
+        print(f"  {dep['word']} --{dep['dep_type']}--> {dep['head']}")
\ No newline at end of file
diff --git a/tools/__init__.py b/tools/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/tools/__pycache__/__init__.cpython-313.pyc b/tools/__pycache__/__init__.cpython-313.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..443a12ccdb2071c1b8b8ff9e25656e9721fcd358
GIT binary patch
literal 151
zcmey&%ge<81P@uCWPs?$AOZ#$p^VQgK*m&tbOudEzm*I{OhDdekkl<R{fzwFRQ-(9
zyrN3|<ouLW{eqmt^u(gf;#}R7)RNTXlFa-({gV9roMQd>_{_Y_lK6PNg34PQHo5sJ
ar8%i~MXW$$K-Lt47$2D#85xV1fh+(CTqK_W

literal 0
HcmV?d00001

diff --git a/tools/__pycache__/parser.cpython-313.pyc b/tools/__pycache__/parser.cpython-313.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..b58fcc99a527fc735bde263bfa61ebba3a2b1481
GIT binary patch
literal 1500
zcmZvc%Wo4$7{F(}4{sJb4&+hS>0^1cU}$ikQX5&hP*mg=jIyzcAY!$6hj`QV?rLTu
zuum3J)kr;n4^heqj^)%V$8zGj5fw25s*vE)TT=f6{bmz~nC?jX&3=#h=KE%TyZvld
zLog1=uNyy$2)*LUV1OQvei^1UWFSNM9uc&N=2N?#ebW(Sq`ne%3?yZU1w=$c0x2yC
zMfo4@xWGoSXV!g!%^UcdNt^ZE_;^(YB;T?BH;6TKWzSbbgS?(_Wl$5;GO+5XCXAzV
z7ZLJO`~0a|YF>&n4+%reAwvS6GGvYwLk6D$KK1{;#9TZ+4e{|A4zDrP9Qs0iQ{(x0
zIAz3ZJ%)-S7uxv+|0nFtTx-pQ{6)7s%WYAI&bE~Wd^4QY+hX~%&)bUrEe>{+Pupqz
z9JXxG6#Zh=fH_tEx~MSGa|0#^#PLEVg|L`OHV#ZCH6WTvfltk%$W)5G5PNmZMBA@3
zIo_7?^VD^neOYSwO<ZbVkF-j4-^QiDwU#X6(B_PdLtGCX-z$Z_@6u9W5sJy_pv6Yx
zS96e=<RDub9_oVVpch(pwejmr=gezqB+`!kC4Kb#;KZu@Le1V$?yRi0yY2f&qp6SY
zU;n-K$K?l?ABxc@<%i$>dG>MTQRQ*<Q8illF*<W8x^y)%?M>6!Fr8@GjjlGMQSYhh
zZ;R;A<d%XmxlW}I`=KG6_!Y)DO#w)2sDwPBh5(Ze#{{m7FL-O5*wrn-`}`C_5S0Kr
zSQD@UYXVSUO+qO-Yf@zLPD!{4rxj1E3G>;vngX>Z?!)lbJ`7XsZ_eHfiB%7E00w(D
z;L*|vb}fF}wBZC)zwQ%#iC94c>;b|2s$(y3C*AOg&14rhn-)_!a$zgLWCXTk8fVYk
zafv`+G0jwmn!$=!4+%$vDY4TeyzO`m;cYR+3V0<&iSQo+%j^~AU`lv%OxrWHC_f*-
zS0|&~qXYZA8}m(sIn)h#55mUap#g{vdO1GX`Qa63^5ucC+jF<)o@FM0sL8^5rCaI2
zwAfwj<=?-j-PL*%?{edMwOj2KKD>AG?#a!<sg1&^-gtg}wmZ9>O;2g7+SV8vncP&T
zH`M9hDo@qp+tZxU4^So_N$(K8b5Uk84Xk>LNv?0%L<U>@-Ndy$KylDcJ8HS<+bb@f
uBRT}}{~<jJVoMYR;W^4cq3O&o%eR)JgNL6eM>^uaN?OSE4~+}?ILUvfPdv>4

literal 0
HcmV?d00001

diff --git a/tools/parser.py b/tools/parser.py
new file mode 100644
index 0000000..63fbfe8
--- /dev/null
+++ b/tools/parser.py
@@ -0,0 +1,35 @@
+import spacy
+
+# English model
+nlp = spacy.load("en_core_web_sm")
+
+# Parse a single sentence
+def parse_sentence(sentence):
+    doc = nlp(sentence)
+
+    print("Token-by-token analysis:")
+    for token in doc:
+        print(f"Text: {token.text:<12} Dep: {token.dep_:<10} Head: {token.head.text:<10} POS: {token.pos_:<8}")
+
+    return doc
+
+def extract_dependency_relationships(doc):
+    """Extract dependency relationships for graph representation"""
+    dependencies = []
+    
+    for token in doc:
+        # Skip punctuation
+        if token.is_punct:
+            continue
+            
+        dependency = {
+            'word': token.text,
+            'lemma': token.lemma_,
+            'dep_type': token.dep_,
+            'head': token.head.text,
+            'head_lemma': token.head.lemma_,
+            'pos': token.pos_
+        }
+        dependencies.append(dependency)
+    
+    return dependencies