Skip to content

Commit 52bff70

Browse files
StatguyUserStatguyUser
committed
Added code or books
1 parent 5a85c2f commit 52bff70

File tree

45 files changed

+428897
-0
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

45 files changed

+428897
-0
lines changed

‎Car details v3.csv

Lines changed: 8129 additions & 0 deletions
Large diffs are not rendered by default.

‎Chapter 1 - Hotel Booking Deman Datasets Preparation.ipynb

Lines changed: 617 additions & 0 deletions
Large diffs are not rendered by default.

‎Chapter 10 - Syntactic N-gram and Dependency Parse Tree.ipynb

Lines changed: 193 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,193 @@
1+
{
2+
"cells": [
3+
{
4+
"cell_type": "code",
5+
"execution_count": 1,
6+
"id": "e79ee373",
7+
"metadata": {},
8+
"outputs": [],
9+
"source": [
10+
"from SNgramExtractor import SNgramExtractor\n",
11+
"import spacy\n",
12+
"from spacy import displacy\n",
13+
"en_nlp = spacy.load('en_core_web_sm')"
14+
]
15+
},
16+
{
17+
"cell_type": "markdown",
18+
"id": "ecd66da8",
19+
"metadata": {},
20+
"source": [
21+
"### Extracting syntactic N-grams"
22+
]
23+
},
24+
{
25+
"cell_type": "code",
26+
"execution_count": 2,
27+
"id": "9165ecf9",
28+
"metadata": {},
29+
"outputs": [
30+
{
31+
"name": "stdout",
32+
"output_type": "stream",
33+
"text": [
34+
"Original Text: You should not run any more\n",
35+
"SNGram bigram: run_You run_should run_not more_any run_more\n",
36+
"SNGram trigram: run_more_any\n"
37+
]
38+
}
39+
],
40+
"source": [
41+
"text = 'You should not run any more'\n",
42+
"\n",
43+
"SNgram_obj=SNgramExtractor(text,\n",
44+
" meta_tag='original',\n",
45+
" trigram_flag='yes',\n",
46+
" nlp_model=None)\n",
47+
"output=SNgram_obj.get_SNgram()\n",
48+
"print('Original Text:',text)\n",
49+
"print('SNGram bigram:',output['SNBigram'])\n",
50+
"print('SNGram trigram:',output['SNTrigram'])"
51+
]
52+
},
53+
{
54+
"cell_type": "code",
55+
"execution_count": null,
56+
"id": "73882fa4",
57+
"metadata": {},
58+
"outputs": [],
59+
"source": []
60+
},
61+
{
62+
"cell_type": "markdown",
63+
"id": "60010f05",
64+
"metadata": {},
65+
"source": [
66+
"### Dependency Parse tree"
67+
]
68+
},
69+
{
70+
"cell_type": "code",
71+
"execution_count": 3,
72+
"id": "99e2c90b",
73+
"metadata": {},
74+
"outputs": [
75+
{
76+
"data": {
77+
"text/html": [
78+
"<span class=\"tex2jax_ignore\"><svg xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\" xml:lang=\"en\" id=\"79c4ca11417542d090928c022c84c842-0\" class=\"displacy\" width=\"950\" height=\"362.0\" direction=\"ltr\" style=\"max-width: none; height: 362.0px; color: #000000; background: #ffffff; font-family: Arial; direction: ltr\">\n",
79+
"<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"272.0\">\n",
80+
" <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"50\">You</tspan>\n",
81+
" <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"50\">PRON</tspan>\n",
82+
"</text>\n",
83+
"\n",
84+
"<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"272.0\">\n",
85+
" <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"200\">should</tspan>\n",
86+
" <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"200\">AUX</tspan>\n",
87+
"</text>\n",
88+
"\n",
89+
"<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"272.0\">\n",
90+
" <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"350\">not</tspan>\n",
91+
" <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"350\">PART</tspan>\n",
92+
"</text>\n",
93+
"\n",
94+
"<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"272.0\">\n",
95+
" <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"500\">run</tspan>\n",
96+
" <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"500\">VERB</tspan>\n",
97+
"</text>\n",
98+
"\n",
99+
"<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"272.0\">\n",
100+
" <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"650\">any</tspan>\n",
101+
" <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"650\">PRON</tspan>\n",
102+
"</text>\n",
103+
"\n",
104+
"<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"272.0\">\n",
105+
" <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"800\">more</tspan>\n",
106+
" <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"800\">ADJ</tspan>\n",
107+
"</text>\n",
108+
"\n",
109+
"<g class=\"displacy-arrow\">\n",
110+
" <path class=\"displacy-arc\" id=\"arrow-79c4ca11417542d090928c022c84c842-0-0\" stroke-width=\"2px\" d=\"M62,227.0 62,152.0 500.0,152.0 500.0,227.0\" fill=\"none\" stroke=\"currentColor\"/>\n",
111+
" <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
112+
" <textPath xlink:href=\"#arrow-79c4ca11417542d090928c022c84c842-0-0\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">nsubj</textPath>\n",
113+
" </text>\n",
114+
" <path class=\"displacy-arrowhead\" d=\"M62,229.0 L58,221.0 66,221.0\" fill=\"currentColor\"/>\n",
115+
"</g>\n",
116+
"\n",
117+
"<g class=\"displacy-arrow\">\n",
118+
" <path class=\"displacy-arc\" id=\"arrow-79c4ca11417542d090928c022c84c842-0-1\" stroke-width=\"2px\" d=\"M212,227.0 212,177.0 497.0,177.0 497.0,227.0\" fill=\"none\" stroke=\"currentColor\"/>\n",
119+
" <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
120+
" <textPath xlink:href=\"#arrow-79c4ca11417542d090928c022c84c842-0-1\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">aux</textPath>\n",
121+
" </text>\n",
122+
" <path class=\"displacy-arrowhead\" d=\"M212,229.0 L208,221.0 216,221.0\" fill=\"currentColor\"/>\n",
123+
"</g>\n",
124+
"\n",
125+
"<g class=\"displacy-arrow\">\n",
126+
" <path class=\"displacy-arc\" id=\"arrow-79c4ca11417542d090928c022c84c842-0-2\" stroke-width=\"2px\" d=\"M362,227.0 362,202.0 494.0,202.0 494.0,227.0\" fill=\"none\" stroke=\"currentColor\"/>\n",
127+
" <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
128+
" <textPath xlink:href=\"#arrow-79c4ca11417542d090928c022c84c842-0-2\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">neg</textPath>\n",
129+
" </text>\n",
130+
" <path class=\"displacy-arrowhead\" d=\"M362,229.0 L358,221.0 366,221.0\" fill=\"currentColor\"/>\n",
131+
"</g>\n",
132+
"\n",
133+
"<g class=\"displacy-arrow\">\n",
134+
" <path class=\"displacy-arc\" id=\"arrow-79c4ca11417542d090928c022c84c842-0-3\" stroke-width=\"2px\" d=\"M662,227.0 662,202.0 794.0,202.0 794.0,227.0\" fill=\"none\" stroke=\"currentColor\"/>\n",
135+
" <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
136+
" <textPath xlink:href=\"#arrow-79c4ca11417542d090928c022c84c842-0-3\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">advmod</textPath>\n",
137+
" </text>\n",
138+
" <path class=\"displacy-arrowhead\" d=\"M662,229.0 L658,221.0 666,221.0\" fill=\"currentColor\"/>\n",
139+
"</g>\n",
140+
"\n",
141+
"<g class=\"displacy-arrow\">\n",
142+
" <path class=\"displacy-arc\" id=\"arrow-79c4ca11417542d090928c022c84c842-0-4\" stroke-width=\"2px\" d=\"M512,227.0 512,177.0 797.0,177.0 797.0,227.0\" fill=\"none\" stroke=\"currentColor\"/>\n",
143+
" <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
144+
" <textPath xlink:href=\"#arrow-79c4ca11417542d090928c022c84c842-0-4\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">advmod</textPath>\n",
145+
" </text>\n",
146+
" <path class=\"displacy-arrowhead\" d=\"M797.0,229.0 L801.0,221.0 793.0,221.0\" fill=\"currentColor\"/>\n",
147+
"</g>\n",
148+
"</svg></span>"
149+
],
150+
"text/plain": [
151+
"<IPython.core.display.HTML object>"
152+
]
153+
},
154+
"metadata": {},
155+
"output_type": "display_data"
156+
}
157+
],
158+
"source": [
159+
"doc = en_nlp(text)\n",
160+
"displacy.render(doc,options={'compact':True})"
161+
]
162+
},
163+
{
164+
"cell_type": "code",
165+
"execution_count": null,
166+
"id": "6ac52371",
167+
"metadata": {},
168+
"outputs": [],
169+
"source": []
170+
}
171+
],
172+
"metadata": {
173+
"kernelspec": {
174+
"display_name": "Python 3 (ipykernel)",
175+
"language": "python",
176+
"name": "python3"
177+
},
178+
"language_info": {
179+
"codemirror_mode": {
180+
"name": "ipython",
181+
"version": 3
182+
},
183+
"file_extension": ".py",
184+
"mimetype": "text/x-python",
185+
"name": "python",
186+
"nbconvert_exporter": "python",
187+
"pygments_lexer": "ipython3",
188+
"version": "3.9.13"
189+
}
190+
},
191+
"nbformat": 4,
192+
"nbformat_minor": 5
193+
}

‎Chapter 11 Baseline Removal.ipynb

Lines changed: 213 additions & 0 deletions
Large diffs are not rendered by default.

‎Chapter 11 Savitzky-Golay Filter.ipynb

Lines changed: 105 additions & 0 deletions
Large diffs are not rendered by default.

‎Chapter 3 - EDA Feature Engineering - Car Sales.ipynb

Lines changed: 425 additions & 0 deletions
Large diffs are not rendered by default.

0 commit comments

Comments
 (0)