Skip to content
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.

Commit cdd5633

Browse files
kshitizrohillakshitizrohilla
committedMay 10, 2023
First Commit
0 parents  commit cdd5633

File tree

3 files changed

+2634
-0
lines changed

3 files changed

+2634
-0
lines changed
 

‎.ipynb_checkpoints/notebook-checkpoint.ipynb

Lines changed: 871 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,871 @@
1+
{
2+
"cells": [
3+
{
4+
"cell_type": "code",
5+
"execution_count": 1,
6+
"id": "56c9e512",
7+
"metadata": {},
8+
"outputs": [],
9+
"source": [
10+
"import numpy as np\n",
11+
"import pandas as pd\n",
12+
"\n",
13+
"import matplotlib.pyplot as plt # for plotting graphs.\n",
14+
"\n",
15+
"from sklearn.model_selection import train_test_split # for splitting the data into training and testing data.\n",
16+
"from sklearn.naive_bayes import GaussianNB # importing the Guassian Naive Bayes model.\n",
17+
"\n",
18+
"np.set_printoptions(suppress=True, precision=6) # set the printing options"
19+
]
20+
},
21+
{
22+
"cell_type": "code",
23+
"execution_count": 2,
24+
"id": "c1944b98",
25+
"metadata": {},
26+
"outputs": [
27+
{
28+
"data": {
29+
"text/html": [
30+
"<div>\n",
31+
"<style scoped>\n",
32+
" .dataframe tbody tr th:only-of-type {\n",
33+
" vertical-align: middle;\n",
34+
" }\n",
35+
"\n",
36+
" .dataframe tbody tr th {\n",
37+
" vertical-align: top;\n",
38+
" }\n",
39+
"\n",
40+
" .dataframe thead th {\n",
41+
" text-align: right;\n",
42+
" }\n",
43+
"</style>\n",
44+
"<table border=\"1\" class=\"dataframe\">\n",
45+
" <thead>\n",
46+
" <tr style=\"text-align: right;\">\n",
47+
" <th></th>\n",
48+
" <th>passenger_id</th>\n",
49+
" <th>name</th>\n",
50+
" <th>p_class</th>\n",
51+
" <th>gender</th>\n",
52+
" <th>age</th>\n",
53+
" <th>sib_sp</th>\n",
54+
" <th>parch</th>\n",
55+
" <th>ticket</th>\n",
56+
" <th>fare</th>\n",
57+
" <th>cabin</th>\n",
58+
" <th>embarked</th>\n",
59+
" <th>survived</th>\n",
60+
" </tr>\n",
61+
" </thead>\n",
62+
" <tbody>\n",
63+
" <tr>\n",
64+
" <th>0</th>\n",
65+
" <td>1</td>\n",
66+
" <td>Braund, Mr. Owen Harris</td>\n",
67+
" <td>3</td>\n",
68+
" <td>male</td>\n",
69+
" <td>22.0</td>\n",
70+
" <td>1</td>\n",
71+
" <td>0</td>\n",
72+
" <td>A/5 21171</td>\n",
73+
" <td>7.2500</td>\n",
74+
" <td>NaN</td>\n",
75+
" <td>S</td>\n",
76+
" <td>0</td>\n",
77+
" </tr>\n",
78+
" <tr>\n",
79+
" <th>1</th>\n",
80+
" <td>2</td>\n",
81+
" <td>Cumings, Mrs. John Bradley (Florence Briggs Th...</td>\n",
82+
" <td>1</td>\n",
83+
" <td>female</td>\n",
84+
" <td>38.0</td>\n",
85+
" <td>1</td>\n",
86+
" <td>0</td>\n",
87+
" <td>PC 17599</td>\n",
88+
" <td>71.2833</td>\n",
89+
" <td>C85</td>\n",
90+
" <td>C</td>\n",
91+
" <td>1</td>\n",
92+
" </tr>\n",
93+
" <tr>\n",
94+
" <th>2</th>\n",
95+
" <td>3</td>\n",
96+
" <td>Heikkinen, Miss. Laina</td>\n",
97+
" <td>3</td>\n",
98+
" <td>female</td>\n",
99+
" <td>26.0</td>\n",
100+
" <td>0</td>\n",
101+
" <td>0</td>\n",
102+
" <td>STON/O2. 3101282</td>\n",
103+
" <td>7.9250</td>\n",
104+
" <td>NaN</td>\n",
105+
" <td>S</td>\n",
106+
" <td>1</td>\n",
107+
" </tr>\n",
108+
" <tr>\n",
109+
" <th>3</th>\n",
110+
" <td>4</td>\n",
111+
" <td>Futrelle, Mrs. Jacques Heath (Lily May Peel)</td>\n",
112+
" <td>1</td>\n",
113+
" <td>female</td>\n",
114+
" <td>35.0</td>\n",
115+
" <td>1</td>\n",
116+
" <td>0</td>\n",
117+
" <td>113803</td>\n",
118+
" <td>53.1000</td>\n",
119+
" <td>C123</td>\n",
120+
" <td>S</td>\n",
121+
" <td>1</td>\n",
122+
" </tr>\n",
123+
" <tr>\n",
124+
" <th>4</th>\n",
125+
" <td>5</td>\n",
126+
" <td>Allen, Mr. William Henry</td>\n",
127+
" <td>3</td>\n",
128+
" <td>male</td>\n",
129+
" <td>35.0</td>\n",
130+
" <td>0</td>\n",
131+
" <td>0</td>\n",
132+
" <td>373450</td>\n",
133+
" <td>8.0500</td>\n",
134+
" <td>NaN</td>\n",
135+
" <td>S</td>\n",
136+
" <td>0</td>\n",
137+
" </tr>\n",
138+
" </tbody>\n",
139+
"</table>\n",
140+
"</div>"
141+
],
142+
"text/plain": [
143+
" passenger_id name p_class \\\n",
144+
"0 1 Braund, Mr. Owen Harris 3 \n",
145+
"1 2 Cumings, Mrs. John Bradley (Florence Briggs Th... 1 \n",
146+
"2 3 Heikkinen, Miss. Laina 3 \n",
147+
"3 4 Futrelle, Mrs. Jacques Heath (Lily May Peel) 1 \n",
148+
"4 5 Allen, Mr. William Henry 3 \n",
149+
"\n",
150+
" gender age sib_sp parch ticket fare cabin embarked \\\n",
151+
"0 male 22.0 1 0 A/5 21171 7.2500 NaN S \n",
152+
"1 female 38.0 1 0 PC 17599 71.2833 C85 C \n",
153+
"2 female 26.0 0 0 STON/O2. 3101282 7.9250 NaN S \n",
154+
"3 female 35.0 1 0 113803 53.1000 C123 S \n",
155+
"4 male 35.0 0 0 373450 8.0500 NaN S \n",
156+
"\n",
157+
" survived \n",
158+
"0 0 \n",
159+
"1 1 \n",
160+
"2 1 \n",
161+
"3 1 \n",
162+
"4 0 "
163+
]
164+
},
165+
"execution_count": 2,
166+
"metadata": {},
167+
"output_type": "execute_result"
168+
}
169+
],
170+
"source": [
171+
"df = pd.read_csv(\"data/titanic-data.csv\")\n",
172+
"df.head()"
173+
]
174+
},
175+
{
176+
"cell_type": "code",
177+
"execution_count": 3,
178+
"id": "d91d3988",
179+
"metadata": {},
180+
"outputs": [
181+
{
182+
"data": {
183+
"text/html": [
184+
"<div>\n",
185+
"<style scoped>\n",
186+
" .dataframe tbody tr th:only-of-type {\n",
187+
" vertical-align: middle;\n",
188+
" }\n",
189+
"\n",
190+
" .dataframe tbody tr th {\n",
191+
" vertical-align: top;\n",
192+
" }\n",
193+
"\n",
194+
" .dataframe thead th {\n",
195+
" text-align: right;\n",
196+
" }\n",
197+
"</style>\n",
198+
"<table border=\"1\" class=\"dataframe\">\n",
199+
" <thead>\n",
200+
" <tr style=\"text-align: right;\">\n",
201+
" <th></th>\n",
202+
" <th>p_class</th>\n",
203+
" <th>gender</th>\n",
204+
" <th>age</th>\n",
205+
" <th>fare</th>\n",
206+
" <th>survived</th>\n",
207+
" </tr>\n",
208+
" </thead>\n",
209+
" <tbody>\n",
210+
" <tr>\n",
211+
" <th>0</th>\n",
212+
" <td>3</td>\n",
213+
" <td>male</td>\n",
214+
" <td>22.0</td>\n",
215+
" <td>7.2500</td>\n",
216+
" <td>0</td>\n",
217+
" </tr>\n",
218+
" <tr>\n",
219+
" <th>1</th>\n",
220+
" <td>1</td>\n",
221+
" <td>female</td>\n",
222+
" <td>38.0</td>\n",
223+
" <td>71.2833</td>\n",
224+
" <td>1</td>\n",
225+
" </tr>\n",
226+
" <tr>\n",
227+
" <th>2</th>\n",
228+
" <td>3</td>\n",
229+
" <td>female</td>\n",
230+
" <td>26.0</td>\n",
231+
" <td>7.9250</td>\n",
232+
" <td>1</td>\n",
233+
" </tr>\n",
234+
" <tr>\n",
235+
" <th>3</th>\n",
236+
" <td>1</td>\n",
237+
" <td>female</td>\n",
238+
" <td>35.0</td>\n",
239+
" <td>53.1000</td>\n",
240+
" <td>1</td>\n",
241+
" </tr>\n",
242+
" <tr>\n",
243+
" <th>4</th>\n",
244+
" <td>3</td>\n",
245+
" <td>male</td>\n",
246+
" <td>35.0</td>\n",
247+
" <td>8.0500</td>\n",
248+
" <td>0</td>\n",
249+
" </tr>\n",
250+
" </tbody>\n",
251+
"</table>\n",
252+
"</div>"
253+
],
254+
"text/plain": [
255+
" p_class gender age fare survived\n",
256+
"0 3 male 22.0 7.2500 0\n",
257+
"1 1 female 38.0 71.2833 1\n",
258+
"2 3 female 26.0 7.9250 1\n",
259+
"3 1 female 35.0 53.1000 1\n",
260+
"4 3 male 35.0 8.0500 0"
261+
]
262+
},
263+
"execution_count": 3,
264+
"metadata": {},
265+
"output_type": "execute_result"
266+
}
267+
],
268+
"source": [
269+
"# dropping certain columns that don't have any impact on the survival rate.\n",
270+
"df.drop([\"passenger_id\", \"name\", \"sib_sp\", \"parch\", \"ticket\", \"cabin\", \"embarked\"], axis=1, inplace=True)\n",
271+
"df.head()"
272+
]
273+
},
274+
{
275+
"cell_type": "code",
276+
"execution_count": 4,
277+
"id": "0a5a4824",
278+
"metadata": {},
279+
"outputs": [
280+
{
281+
"data": {
282+
"text/plain": [
283+
"0 0\n",
284+
"1 1\n",
285+
"2 1\n",
286+
"3 1\n",
287+
"4 0\n",
288+
"Name: survived, dtype: int64"
289+
]
290+
},
291+
"metadata": {},
292+
"output_type": "display_data"
293+
},
294+
{
295+
"data": {
296+
"text/html": [
297+
"<div>\n",
298+
"<style scoped>\n",
299+
" .dataframe tbody tr th:only-of-type {\n",
300+
" vertical-align: middle;\n",
301+
" }\n",
302+
"\n",
303+
" .dataframe tbody tr th {\n",
304+
" vertical-align: top;\n",
305+
" }\n",
306+
"\n",
307+
" .dataframe thead th {\n",
308+
" text-align: right;\n",
309+
" }\n",
310+
"</style>\n",
311+
"<table border=\"1\" class=\"dataframe\">\n",
312+
" <thead>\n",
313+
" <tr style=\"text-align: right;\">\n",
314+
" <th></th>\n",
315+
" <th>p_class</th>\n",
316+
" <th>gender</th>\n",
317+
" <th>age</th>\n",
318+
" <th>fare</th>\n",
319+
" </tr>\n",
320+
" </thead>\n",
321+
" <tbody>\n",
322+
" <tr>\n",
323+
" <th>0</th>\n",
324+
" <td>3</td>\n",
325+
" <td>male</td>\n",
326+
" <td>22.0</td>\n",
327+
" <td>7.2500</td>\n",
328+
" </tr>\n",
329+
" <tr>\n",
330+
" <th>1</th>\n",
331+
" <td>1</td>\n",
332+
" <td>female</td>\n",
333+
" <td>38.0</td>\n",
334+
" <td>71.2833</td>\n",
335+
" </tr>\n",
336+
" <tr>\n",
337+
" <th>2</th>\n",
338+
" <td>3</td>\n",
339+
" <td>female</td>\n",
340+
" <td>26.0</td>\n",
341+
" <td>7.9250</td>\n",
342+
" </tr>\n",
343+
" <tr>\n",
344+
" <th>3</th>\n",
345+
" <td>1</td>\n",
346+
" <td>female</td>\n",
347+
" <td>35.0</td>\n",
348+
" <td>53.1000</td>\n",
349+
" </tr>\n",
350+
" <tr>\n",
351+
" <th>4</th>\n",
352+
" <td>3</td>\n",
353+
" <td>male</td>\n",
354+
" <td>35.0</td>\n",
355+
" <td>8.0500</td>\n",
356+
" </tr>\n",
357+
" </tbody>\n",
358+
"</table>\n",
359+
"</div>"
360+
],
361+
"text/plain": [
362+
" p_class gender age fare\n",
363+
"0 3 male 22.0 7.2500\n",
364+
"1 1 female 38.0 71.2833\n",
365+
"2 3 female 26.0 7.9250\n",
366+
"3 1 female 35.0 53.1000\n",
367+
"4 3 male 35.0 8.0500"
368+
]
369+
},
370+
"metadata": {},
371+
"output_type": "display_data"
372+
}
373+
],
374+
"source": [
375+
"target = df[\"survived\"] # creating a series for the survived column.\n",
376+
"inputs = df.drop(\"survived\", axis=1) # creating a separate dataframe by removing the survived column.\n",
377+
"\n",
378+
"display(target.head())\n",
379+
"display(inputs.head())"
380+
]
381+
},
382+
{
383+
"cell_type": "code",
384+
"execution_count": 5,
385+
"id": "69849efe",
386+
"metadata": {},
387+
"outputs": [
388+
{
389+
"data": {
390+
"text/html": [
391+
"<div>\n",
392+
"<style scoped>\n",
393+
" .dataframe tbody tr th:only-of-type {\n",
394+
" vertical-align: middle;\n",
395+
" }\n",
396+
"\n",
397+
" .dataframe tbody tr th {\n",
398+
" vertical-align: top;\n",
399+
" }\n",
400+
"\n",
401+
" .dataframe thead th {\n",
402+
" text-align: right;\n",
403+
" }\n",
404+
"</style>\n",
405+
"<table border=\"1\" class=\"dataframe\">\n",
406+
" <thead>\n",
407+
" <tr style=\"text-align: right;\">\n",
408+
" <th></th>\n",
409+
" <th>female</th>\n",
410+
" <th>male</th>\n",
411+
" </tr>\n",
412+
" </thead>\n",
413+
" <tbody>\n",
414+
" <tr>\n",
415+
" <th>0</th>\n",
416+
" <td>0</td>\n",
417+
" <td>1</td>\n",
418+
" </tr>\n",
419+
" <tr>\n",
420+
" <th>1</th>\n",
421+
" <td>1</td>\n",
422+
" <td>0</td>\n",
423+
" </tr>\n",
424+
" <tr>\n",
425+
" <th>2</th>\n",
426+
" <td>1</td>\n",
427+
" <td>0</td>\n",
428+
" </tr>\n",
429+
" <tr>\n",
430+
" <th>3</th>\n",
431+
" <td>1</td>\n",
432+
" <td>0</td>\n",
433+
" </tr>\n",
434+
" <tr>\n",
435+
" <th>4</th>\n",
436+
" <td>0</td>\n",
437+
" <td>1</td>\n",
438+
" </tr>\n",
439+
" </tbody>\n",
440+
"</table>\n",
441+
"</div>"
442+
],
443+
"text/plain": [
444+
" female male\n",
445+
"0 0 1\n",
446+
"1 1 0\n",
447+
"2 1 0\n",
448+
"3 1 0\n",
449+
"4 0 1"
450+
]
451+
},
452+
"metadata": {},
453+
"output_type": "display_data"
454+
},
455+
{
456+
"name": "stdout",
457+
"output_type": "stream",
458+
"text": [
459+
"female uint8\n",
460+
"male uint8\n",
461+
"dtype: object\n"
462+
]
463+
}
464+
],
465+
"source": [
466+
"dummies = pd.get_dummies(inputs[\"gender\"]) # converting the gender column into dummy variables.\n",
467+
"\n",
468+
"display(dummies.head())\n",
469+
"print(dummies.dtypes)"
470+
]
471+
},
472+
{
473+
"cell_type": "code",
474+
"execution_count": 6,
475+
"id": "9bdf780c",
476+
"metadata": {},
477+
"outputs": [
478+
{
479+
"data": {
480+
"text/html": [
481+
"<div>\n",
482+
"<style scoped>\n",
483+
" .dataframe tbody tr th:only-of-type {\n",
484+
" vertical-align: middle;\n",
485+
" }\n",
486+
"\n",
487+
" .dataframe tbody tr th {\n",
488+
" vertical-align: top;\n",
489+
" }\n",
490+
"\n",
491+
" .dataframe thead th {\n",
492+
" text-align: right;\n",
493+
" }\n",
494+
"</style>\n",
495+
"<table border=\"1\" class=\"dataframe\">\n",
496+
" <thead>\n",
497+
" <tr style=\"text-align: right;\">\n",
498+
" <th></th>\n",
499+
" <th>p_class</th>\n",
500+
" <th>gender</th>\n",
501+
" <th>age</th>\n",
502+
" <th>fare</th>\n",
503+
" <th>female</th>\n",
504+
" <th>male</th>\n",
505+
" </tr>\n",
506+
" </thead>\n",
507+
" <tbody>\n",
508+
" <tr>\n",
509+
" <th>0</th>\n",
510+
" <td>3</td>\n",
511+
" <td>male</td>\n",
512+
" <td>22.0</td>\n",
513+
" <td>7.2500</td>\n",
514+
" <td>0</td>\n",
515+
" <td>1</td>\n",
516+
" </tr>\n",
517+
" <tr>\n",
518+
" <th>1</th>\n",
519+
" <td>1</td>\n",
520+
" <td>female</td>\n",
521+
" <td>38.0</td>\n",
522+
" <td>71.2833</td>\n",
523+
" <td>1</td>\n",
524+
" <td>0</td>\n",
525+
" </tr>\n",
526+
" <tr>\n",
527+
" <th>2</th>\n",
528+
" <td>3</td>\n",
529+
" <td>female</td>\n",
530+
" <td>26.0</td>\n",
531+
" <td>7.9250</td>\n",
532+
" <td>1</td>\n",
533+
" <td>0</td>\n",
534+
" </tr>\n",
535+
" <tr>\n",
536+
" <th>3</th>\n",
537+
" <td>1</td>\n",
538+
" <td>female</td>\n",
539+
" <td>35.0</td>\n",
540+
" <td>53.1000</td>\n",
541+
" <td>1</td>\n",
542+
" <td>0</td>\n",
543+
" </tr>\n",
544+
" <tr>\n",
545+
" <th>4</th>\n",
546+
" <td>3</td>\n",
547+
" <td>male</td>\n",
548+
" <td>35.0</td>\n",
549+
" <td>8.0500</td>\n",
550+
" <td>0</td>\n",
551+
" <td>1</td>\n",
552+
" </tr>\n",
553+
" </tbody>\n",
554+
"</table>\n",
555+
"</div>"
556+
],
557+
"text/plain": [
558+
" p_class gender age fare female male\n",
559+
"0 3 male 22.0 7.2500 0 1\n",
560+
"1 1 female 38.0 71.2833 1 0\n",
561+
"2 3 female 26.0 7.9250 1 0\n",
562+
"3 1 female 35.0 53.1000 1 0\n",
563+
"4 3 male 35.0 8.0500 0 1"
564+
]
565+
},
566+
"execution_count": 6,
567+
"metadata": {},
568+
"output_type": "execute_result"
569+
}
570+
],
571+
"source": [
572+
"# concatenating the inputs dataframe with the dummies dataframe.\n",
573+
"inputs = pd.concat([inputs, dummies], axis=1)\n",
574+
"inputs.head()"
575+
]
576+
},
577+
{
578+
"cell_type": "code",
579+
"execution_count": 7,
580+
"id": "24fcccc2",
581+
"metadata": {},
582+
"outputs": [
583+
{
584+
"data": {
585+
"text/html": [
586+
"<div>\n",
587+
"<style scoped>\n",
588+
" .dataframe tbody tr th:only-of-type {\n",
589+
" vertical-align: middle;\n",
590+
" }\n",
591+
"\n",
592+
" .dataframe tbody tr th {\n",
593+
" vertical-align: top;\n",
594+
" }\n",
595+
"\n",
596+
" .dataframe thead th {\n",
597+
" text-align: right;\n",
598+
" }\n",
599+
"</style>\n",
600+
"<table border=\"1\" class=\"dataframe\">\n",
601+
" <thead>\n",
602+
" <tr style=\"text-align: right;\">\n",
603+
" <th></th>\n",
604+
" <th>p_class</th>\n",
605+
" <th>age</th>\n",
606+
" <th>fare</th>\n",
607+
" <th>female</th>\n",
608+
" <th>male</th>\n",
609+
" </tr>\n",
610+
" </thead>\n",
611+
" <tbody>\n",
612+
" <tr>\n",
613+
" <th>0</th>\n",
614+
" <td>3</td>\n",
615+
" <td>22.0</td>\n",
616+
" <td>7.2500</td>\n",
617+
" <td>0</td>\n",
618+
" <td>1</td>\n",
619+
" </tr>\n",
620+
" <tr>\n",
621+
" <th>1</th>\n",
622+
" <td>1</td>\n",
623+
" <td>38.0</td>\n",
624+
" <td>71.2833</td>\n",
625+
" <td>1</td>\n",
626+
" <td>0</td>\n",
627+
" </tr>\n",
628+
" <tr>\n",
629+
" <th>2</th>\n",
630+
" <td>3</td>\n",
631+
" <td>26.0</td>\n",
632+
" <td>7.9250</td>\n",
633+
" <td>1</td>\n",
634+
" <td>0</td>\n",
635+
" </tr>\n",
636+
" <tr>\n",
637+
" <th>3</th>\n",
638+
" <td>1</td>\n",
639+
" <td>35.0</td>\n",
640+
" <td>53.1000</td>\n",
641+
" <td>1</td>\n",
642+
" <td>0</td>\n",
643+
" </tr>\n",
644+
" <tr>\n",
645+
" <th>4</th>\n",
646+
" <td>3</td>\n",
647+
" <td>35.0</td>\n",
648+
" <td>8.0500</td>\n",
649+
" <td>0</td>\n",
650+
" <td>1</td>\n",
651+
" </tr>\n",
652+
" </tbody>\n",
653+
"</table>\n",
654+
"</div>"
655+
],
656+
"text/plain": [
657+
" p_class age fare female male\n",
658+
"0 3 22.0 7.2500 0 1\n",
659+
"1 1 38.0 71.2833 1 0\n",
660+
"2 3 26.0 7.9250 1 0\n",
661+
"3 1 35.0 53.1000 1 0\n",
662+
"4 3 35.0 8.0500 0 1"
663+
]
664+
},
665+
"execution_count": 7,
666+
"metadata": {},
667+
"output_type": "execute_result"
668+
}
669+
],
670+
"source": [
671+
"# dropping the gender column because we now have the female and male columns.\n",
672+
"inputs.drop([\"gender\"], axis=1, inplace=True)\n",
673+
"inputs.head()"
674+
]
675+
},
676+
{
677+
"cell_type": "code",
678+
"execution_count": 8,
679+
"id": "c8f8c764",
680+
"metadata": {},
681+
"outputs": [
682+
{
683+
"data": {
684+
"text/plain": [
685+
"0 22.0\n",
686+
"1 38.0\n",
687+
"2 26.0\n",
688+
"3 35.0\n",
689+
"4 35.0\n",
690+
"5 NaN\n",
691+
"6 54.0\n",
692+
"7 2.0\n",
693+
"8 27.0\n",
694+
"9 14.0\n",
695+
"Name: age, dtype: float64"
696+
]
697+
},
698+
"execution_count": 8,
699+
"metadata": {},
700+
"output_type": "execute_result"
701+
}
702+
],
703+
"source": [
704+
"# it can be observed that some columns contains null values.\n",
705+
"inputs.age[:10]"
706+
]
707+
},
708+
{
709+
"cell_type": "code",
710+
"execution_count": 9,
711+
"id": "c9c01a43",
712+
"metadata": {},
713+
"outputs": [
714+
{
715+
"data": {
716+
"text/plain": [
717+
"0 22.000000\n",
718+
"1 38.000000\n",
719+
"2 26.000000\n",
720+
"3 35.000000\n",
721+
"4 35.000000\n",
722+
"5 29.699118\n",
723+
"6 54.000000\n",
724+
"7 2.000000\n",
725+
"8 27.000000\n",
726+
"9 14.000000\n",
727+
"Name: age, dtype: float64"
728+
]
729+
},
730+
"execution_count": 9,
731+
"metadata": {},
732+
"output_type": "execute_result"
733+
}
734+
],
735+
"source": [
736+
"# one way of handling these null values is to fill those values with the mean value of the whole column.\n",
737+
"# we can also make these values an integer type values.\n",
738+
"inputs[\"age\"] = inputs[\"age\"].fillna(inputs[\"age\"].mean())\n",
739+
"\n",
740+
"inputs.age[:10]\n",
741+
"# as we can see the 5th row in the earlier cell was null and now it is replaced with the mean value."
742+
]
743+
},
744+
{
745+
"cell_type": "code",
746+
"execution_count": 10,
747+
"id": "5bda4746",
748+
"metadata": {},
749+
"outputs": [
750+
{
751+
"name": "stdout",
752+
"output_type": "stream",
753+
"text": [
754+
"712 179 891\n",
755+
"0.7991021324354658\n",
756+
"0.20089786756453423\n"
757+
]
758+
}
759+
],
760+
"source": [
761+
"X_train, X_test, y_train, y_test = train_test_split(inputs, target, test_size=0.2)\n",
762+
"# 20% test size and 80% train size.\n",
763+
"print(len(X_train), len(X_test), len(inputs))\n",
764+
"\n",
765+
"# calculating training and testing data percentage.\n",
766+
"print(len(X_train) / len(inputs)) # training data %\n",
767+
"print(len(X_test) / len(inputs)) # testing data %"
768+
]
769+
},
770+
{
771+
"cell_type": "code",
772+
"execution_count": 11,
773+
"id": "42deb68a",
774+
"metadata": {},
775+
"outputs": [
776+
{
777+
"data": {
778+
"text/html": [
779+
"<style>#sk-container-id-1 {color: black;background-color: white;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-1 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-1 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-1 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>GaussianNB()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">GaussianNB</label><div class=\"sk-toggleable__content\"><pre>GaussianNB()</pre></div></div></div></div></div>"
780+
],
781+
"text/plain": [
782+
"GaussianNB()"
783+
]
784+
},
785+
"execution_count": 11,
786+
"metadata": {},
787+
"output_type": "execute_result"
788+
}
789+
],
790+
"source": [
791+
"# we are using the Gaussian Naive Bayes model.\n",
792+
"model = GaussianNB()\n",
793+
"model.fit(X_train, y_train)"
794+
]
795+
},
796+
{
797+
"cell_type": "code",
798+
"execution_count": 12,
799+
"id": "422daf07",
800+
"metadata": {},
801+
"outputs": [
802+
{
803+
"data": {
804+
"text/plain": [
805+
"0.7374301675977654"
806+
]
807+
},
808+
"execution_count": 12,
809+
"metadata": {},
810+
"output_type": "execute_result"
811+
}
812+
],
813+
"source": [
814+
"model.score(X_test, y_test)"
815+
]
816+
},
817+
{
818+
"cell_type": "code",
819+
"execution_count": 13,
820+
"id": "ec58fa13",
821+
"metadata": {},
822+
"outputs": [
823+
{
824+
"name": "stdout",
825+
"output_type": "stream",
826+
"text": [
827+
"[0 0 1 0 0]\n",
828+
"0.9931484209536514, 0.015823706167673823, 0.9932294253552363, 0.9833500719459427, 0.9919031866574911, "
829+
]
830+
}
831+
],
832+
"source": [
833+
"pred = np.array(model.predict(X_test))\n",
834+
"pred_probability = np.array(model.predict_proba(X_test)) # calculating the probabilities\n",
835+
"\n",
836+
"print(pred[:5])\n",
837+
"for i in range(1, 6):\n",
838+
" print(pred_probability[i][0], end=\", \")"
839+
]
840+
},
841+
{
842+
"cell_type": "code",
843+
"execution_count": null,
844+
"id": "25eed843",
845+
"metadata": {},
846+
"outputs": [],
847+
"source": []
848+
}
849+
],
850+
"metadata": {
851+
"kernelspec": {
852+
"display_name": "Python 3 (ipykernel)",
853+
"language": "python",
854+
"name": "python3"
855+
},
856+
"language_info": {
857+
"codemirror_mode": {
858+
"name": "ipython",
859+
"version": 3
860+
},
861+
"file_extension": ".py",
862+
"mimetype": "text/x-python",
863+
"name": "python",
864+
"nbconvert_exporter": "python",
865+
"pygments_lexer": "ipython3",
866+
"version": "3.11.2"
867+
}
868+
},
869+
"nbformat": 4,
870+
"nbformat_minor": 5
871+
}

‎data/titanic-data.csv

Lines changed: 892 additions & 0 deletions
Large diffs are not rendered by default.

‎notebook.ipynb

Lines changed: 871 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,871 @@
1+
{
2+
"cells": [
3+
{
4+
"cell_type": "code",
5+
"execution_count": 1,
6+
"id": "56c9e512",
7+
"metadata": {},
8+
"outputs": [],
9+
"source": [
10+
"import numpy as np\n",
11+
"import pandas as pd\n",
12+
"\n",
13+
"import matplotlib.pyplot as plt # for plotting graphs.\n",
14+
"\n",
15+
"from sklearn.model_selection import train_test_split # for splitting the data into training and testing data.\n",
16+
"from sklearn.naive_bayes import GaussianNB # importing the Guassian Naive Bayes model.\n",
17+
"\n",
18+
"np.set_printoptions(suppress=True, precision=6) # set the printing options"
19+
]
20+
},
21+
{
22+
"cell_type": "code",
23+
"execution_count": 2,
24+
"id": "c1944b98",
25+
"metadata": {},
26+
"outputs": [
27+
{
28+
"data": {
29+
"text/html": [
30+
"<div>\n",
31+
"<style scoped>\n",
32+
" .dataframe tbody tr th:only-of-type {\n",
33+
" vertical-align: middle;\n",
34+
" }\n",
35+
"\n",
36+
" .dataframe tbody tr th {\n",
37+
" vertical-align: top;\n",
38+
" }\n",
39+
"\n",
40+
" .dataframe thead th {\n",
41+
" text-align: right;\n",
42+
" }\n",
43+
"</style>\n",
44+
"<table border=\"1\" class=\"dataframe\">\n",
45+
" <thead>\n",
46+
" <tr style=\"text-align: right;\">\n",
47+
" <th></th>\n",
48+
" <th>passenger_id</th>\n",
49+
" <th>name</th>\n",
50+
" <th>p_class</th>\n",
51+
" <th>gender</th>\n",
52+
" <th>age</th>\n",
53+
" <th>sib_sp</th>\n",
54+
" <th>parch</th>\n",
55+
" <th>ticket</th>\n",
56+
" <th>fare</th>\n",
57+
" <th>cabin</th>\n",
58+
" <th>embarked</th>\n",
59+
" <th>survived</th>\n",
60+
" </tr>\n",
61+
" </thead>\n",
62+
" <tbody>\n",
63+
" <tr>\n",
64+
" <th>0</th>\n",
65+
" <td>1</td>\n",
66+
" <td>Braund, Mr. Owen Harris</td>\n",
67+
" <td>3</td>\n",
68+
" <td>male</td>\n",
69+
" <td>22.0</td>\n",
70+
" <td>1</td>\n",
71+
" <td>0</td>\n",
72+
" <td>A/5 21171</td>\n",
73+
" <td>7.2500</td>\n",
74+
" <td>NaN</td>\n",
75+
" <td>S</td>\n",
76+
" <td>0</td>\n",
77+
" </tr>\n",
78+
" <tr>\n",
79+
" <th>1</th>\n",
80+
" <td>2</td>\n",
81+
" <td>Cumings, Mrs. John Bradley (Florence Briggs Th...</td>\n",
82+
" <td>1</td>\n",
83+
" <td>female</td>\n",
84+
" <td>38.0</td>\n",
85+
" <td>1</td>\n",
86+
" <td>0</td>\n",
87+
" <td>PC 17599</td>\n",
88+
" <td>71.2833</td>\n",
89+
" <td>C85</td>\n",
90+
" <td>C</td>\n",
91+
" <td>1</td>\n",
92+
" </tr>\n",
93+
" <tr>\n",
94+
" <th>2</th>\n",
95+
" <td>3</td>\n",
96+
" <td>Heikkinen, Miss. Laina</td>\n",
97+
" <td>3</td>\n",
98+
" <td>female</td>\n",
99+
" <td>26.0</td>\n",
100+
" <td>0</td>\n",
101+
" <td>0</td>\n",
102+
" <td>STON/O2. 3101282</td>\n",
103+
" <td>7.9250</td>\n",
104+
" <td>NaN</td>\n",
105+
" <td>S</td>\n",
106+
" <td>1</td>\n",
107+
" </tr>\n",
108+
" <tr>\n",
109+
" <th>3</th>\n",
110+
" <td>4</td>\n",
111+
" <td>Futrelle, Mrs. Jacques Heath (Lily May Peel)</td>\n",
112+
" <td>1</td>\n",
113+
" <td>female</td>\n",
114+
" <td>35.0</td>\n",
115+
" <td>1</td>\n",
116+
" <td>0</td>\n",
117+
" <td>113803</td>\n",
118+
" <td>53.1000</td>\n",
119+
" <td>C123</td>\n",
120+
" <td>S</td>\n",
121+
" <td>1</td>\n",
122+
" </tr>\n",
123+
" <tr>\n",
124+
" <th>4</th>\n",
125+
" <td>5</td>\n",
126+
" <td>Allen, Mr. William Henry</td>\n",
127+
" <td>3</td>\n",
128+
" <td>male</td>\n",
129+
" <td>35.0</td>\n",
130+
" <td>0</td>\n",
131+
" <td>0</td>\n",
132+
" <td>373450</td>\n",
133+
" <td>8.0500</td>\n",
134+
" <td>NaN</td>\n",
135+
" <td>S</td>\n",
136+
" <td>0</td>\n",
137+
" </tr>\n",
138+
" </tbody>\n",
139+
"</table>\n",
140+
"</div>"
141+
],
142+
"text/plain": [
143+
" passenger_id name p_class \\\n",
144+
"0 1 Braund, Mr. Owen Harris 3 \n",
145+
"1 2 Cumings, Mrs. John Bradley (Florence Briggs Th... 1 \n",
146+
"2 3 Heikkinen, Miss. Laina 3 \n",
147+
"3 4 Futrelle, Mrs. Jacques Heath (Lily May Peel) 1 \n",
148+
"4 5 Allen, Mr. William Henry 3 \n",
149+
"\n",
150+
" gender age sib_sp parch ticket fare cabin embarked \\\n",
151+
"0 male 22.0 1 0 A/5 21171 7.2500 NaN S \n",
152+
"1 female 38.0 1 0 PC 17599 71.2833 C85 C \n",
153+
"2 female 26.0 0 0 STON/O2. 3101282 7.9250 NaN S \n",
154+
"3 female 35.0 1 0 113803 53.1000 C123 S \n",
155+
"4 male 35.0 0 0 373450 8.0500 NaN S \n",
156+
"\n",
157+
" survived \n",
158+
"0 0 \n",
159+
"1 1 \n",
160+
"2 1 \n",
161+
"3 1 \n",
162+
"4 0 "
163+
]
164+
},
165+
"execution_count": 2,
166+
"metadata": {},
167+
"output_type": "execute_result"
168+
}
169+
],
170+
"source": [
171+
"df = pd.read_csv(\"data/titanic-data.csv\")\n",
172+
"df.head()"
173+
]
174+
},
175+
{
176+
"cell_type": "code",
177+
"execution_count": 3,
178+
"id": "d91d3988",
179+
"metadata": {},
180+
"outputs": [
181+
{
182+
"data": {
183+
"text/html": [
184+
"<div>\n",
185+
"<style scoped>\n",
186+
" .dataframe tbody tr th:only-of-type {\n",
187+
" vertical-align: middle;\n",
188+
" }\n",
189+
"\n",
190+
" .dataframe tbody tr th {\n",
191+
" vertical-align: top;\n",
192+
" }\n",
193+
"\n",
194+
" .dataframe thead th {\n",
195+
" text-align: right;\n",
196+
" }\n",
197+
"</style>\n",
198+
"<table border=\"1\" class=\"dataframe\">\n",
199+
" <thead>\n",
200+
" <tr style=\"text-align: right;\">\n",
201+
" <th></th>\n",
202+
" <th>p_class</th>\n",
203+
" <th>gender</th>\n",
204+
" <th>age</th>\n",
205+
" <th>fare</th>\n",
206+
" <th>survived</th>\n",
207+
" </tr>\n",
208+
" </thead>\n",
209+
" <tbody>\n",
210+
" <tr>\n",
211+
" <th>0</th>\n",
212+
" <td>3</td>\n",
213+
" <td>male</td>\n",
214+
" <td>22.0</td>\n",
215+
" <td>7.2500</td>\n",
216+
" <td>0</td>\n",
217+
" </tr>\n",
218+
" <tr>\n",
219+
" <th>1</th>\n",
220+
" <td>1</td>\n",
221+
" <td>female</td>\n",
222+
" <td>38.0</td>\n",
223+
" <td>71.2833</td>\n",
224+
" <td>1</td>\n",
225+
" </tr>\n",
226+
" <tr>\n",
227+
" <th>2</th>\n",
228+
" <td>3</td>\n",
229+
" <td>female</td>\n",
230+
" <td>26.0</td>\n",
231+
" <td>7.9250</td>\n",
232+
" <td>1</td>\n",
233+
" </tr>\n",
234+
" <tr>\n",
235+
" <th>3</th>\n",
236+
" <td>1</td>\n",
237+
" <td>female</td>\n",
238+
" <td>35.0</td>\n",
239+
" <td>53.1000</td>\n",
240+
" <td>1</td>\n",
241+
" </tr>\n",
242+
" <tr>\n",
243+
" <th>4</th>\n",
244+
" <td>3</td>\n",
245+
" <td>male</td>\n",
246+
" <td>35.0</td>\n",
247+
" <td>8.0500</td>\n",
248+
" <td>0</td>\n",
249+
" </tr>\n",
250+
" </tbody>\n",
251+
"</table>\n",
252+
"</div>"
253+
],
254+
"text/plain": [
255+
" p_class gender age fare survived\n",
256+
"0 3 male 22.0 7.2500 0\n",
257+
"1 1 female 38.0 71.2833 1\n",
258+
"2 3 female 26.0 7.9250 1\n",
259+
"3 1 female 35.0 53.1000 1\n",
260+
"4 3 male 35.0 8.0500 0"
261+
]
262+
},
263+
"execution_count": 3,
264+
"metadata": {},
265+
"output_type": "execute_result"
266+
}
267+
],
268+
"source": [
269+
"# dropping certain columns that don't have any impact on the survival rate.\n",
270+
"df.drop([\"passenger_id\", \"name\", \"sib_sp\", \"parch\", \"ticket\", \"cabin\", \"embarked\"], axis=1, inplace=True)\n",
271+
"df.head()"
272+
]
273+
},
274+
{
275+
"cell_type": "code",
276+
"execution_count": 4,
277+
"id": "0a5a4824",
278+
"metadata": {},
279+
"outputs": [
280+
{
281+
"data": {
282+
"text/plain": [
283+
"0 0\n",
284+
"1 1\n",
285+
"2 1\n",
286+
"3 1\n",
287+
"4 0\n",
288+
"Name: survived, dtype: int64"
289+
]
290+
},
291+
"metadata": {},
292+
"output_type": "display_data"
293+
},
294+
{
295+
"data": {
296+
"text/html": [
297+
"<div>\n",
298+
"<style scoped>\n",
299+
" .dataframe tbody tr th:only-of-type {\n",
300+
" vertical-align: middle;\n",
301+
" }\n",
302+
"\n",
303+
" .dataframe tbody tr th {\n",
304+
" vertical-align: top;\n",
305+
" }\n",
306+
"\n",
307+
" .dataframe thead th {\n",
308+
" text-align: right;\n",
309+
" }\n",
310+
"</style>\n",
311+
"<table border=\"1\" class=\"dataframe\">\n",
312+
" <thead>\n",
313+
" <tr style=\"text-align: right;\">\n",
314+
" <th></th>\n",
315+
" <th>p_class</th>\n",
316+
" <th>gender</th>\n",
317+
" <th>age</th>\n",
318+
" <th>fare</th>\n",
319+
" </tr>\n",
320+
" </thead>\n",
321+
" <tbody>\n",
322+
" <tr>\n",
323+
" <th>0</th>\n",
324+
" <td>3</td>\n",
325+
" <td>male</td>\n",
326+
" <td>22.0</td>\n",
327+
" <td>7.2500</td>\n",
328+
" </tr>\n",
329+
" <tr>\n",
330+
" <th>1</th>\n",
331+
" <td>1</td>\n",
332+
" <td>female</td>\n",
333+
" <td>38.0</td>\n",
334+
" <td>71.2833</td>\n",
335+
" </tr>\n",
336+
" <tr>\n",
337+
" <th>2</th>\n",
338+
" <td>3</td>\n",
339+
" <td>female</td>\n",
340+
" <td>26.0</td>\n",
341+
" <td>7.9250</td>\n",
342+
" </tr>\n",
343+
" <tr>\n",
344+
" <th>3</th>\n",
345+
" <td>1</td>\n",
346+
" <td>female</td>\n",
347+
" <td>35.0</td>\n",
348+
" <td>53.1000</td>\n",
349+
" </tr>\n",
350+
" <tr>\n",
351+
" <th>4</th>\n",
352+
" <td>3</td>\n",
353+
" <td>male</td>\n",
354+
" <td>35.0</td>\n",
355+
" <td>8.0500</td>\n",
356+
" </tr>\n",
357+
" </tbody>\n",
358+
"</table>\n",
359+
"</div>"
360+
],
361+
"text/plain": [
362+
" p_class gender age fare\n",
363+
"0 3 male 22.0 7.2500\n",
364+
"1 1 female 38.0 71.2833\n",
365+
"2 3 female 26.0 7.9250\n",
366+
"3 1 female 35.0 53.1000\n",
367+
"4 3 male 35.0 8.0500"
368+
]
369+
},
370+
"metadata": {},
371+
"output_type": "display_data"
372+
}
373+
],
374+
"source": [
375+
"target = df[\"survived\"] # creating a series for the survived column.\n",
376+
"inputs = df.drop(\"survived\", axis=1) # creating a separate dataframe by removing the survived column.\n",
377+
"\n",
378+
"display(target.head())\n",
379+
"display(inputs.head())"
380+
]
381+
},
382+
{
383+
"cell_type": "code",
384+
"execution_count": 5,
385+
"id": "69849efe",
386+
"metadata": {},
387+
"outputs": [
388+
{
389+
"data": {
390+
"text/html": [
391+
"<div>\n",
392+
"<style scoped>\n",
393+
" .dataframe tbody tr th:only-of-type {\n",
394+
" vertical-align: middle;\n",
395+
" }\n",
396+
"\n",
397+
" .dataframe tbody tr th {\n",
398+
" vertical-align: top;\n",
399+
" }\n",
400+
"\n",
401+
" .dataframe thead th {\n",
402+
" text-align: right;\n",
403+
" }\n",
404+
"</style>\n",
405+
"<table border=\"1\" class=\"dataframe\">\n",
406+
" <thead>\n",
407+
" <tr style=\"text-align: right;\">\n",
408+
" <th></th>\n",
409+
" <th>female</th>\n",
410+
" <th>male</th>\n",
411+
" </tr>\n",
412+
" </thead>\n",
413+
" <tbody>\n",
414+
" <tr>\n",
415+
" <th>0</th>\n",
416+
" <td>0</td>\n",
417+
" <td>1</td>\n",
418+
" </tr>\n",
419+
" <tr>\n",
420+
" <th>1</th>\n",
421+
" <td>1</td>\n",
422+
" <td>0</td>\n",
423+
" </tr>\n",
424+
" <tr>\n",
425+
" <th>2</th>\n",
426+
" <td>1</td>\n",
427+
" <td>0</td>\n",
428+
" </tr>\n",
429+
" <tr>\n",
430+
" <th>3</th>\n",
431+
" <td>1</td>\n",
432+
" <td>0</td>\n",
433+
" </tr>\n",
434+
" <tr>\n",
435+
" <th>4</th>\n",
436+
" <td>0</td>\n",
437+
" <td>1</td>\n",
438+
" </tr>\n",
439+
" </tbody>\n",
440+
"</table>\n",
441+
"</div>"
442+
],
443+
"text/plain": [
444+
" female male\n",
445+
"0 0 1\n",
446+
"1 1 0\n",
447+
"2 1 0\n",
448+
"3 1 0\n",
449+
"4 0 1"
450+
]
451+
},
452+
"metadata": {},
453+
"output_type": "display_data"
454+
},
455+
{
456+
"name": "stdout",
457+
"output_type": "stream",
458+
"text": [
459+
"female uint8\n",
460+
"male uint8\n",
461+
"dtype: object\n"
462+
]
463+
}
464+
],
465+
"source": [
466+
"dummies = pd.get_dummies(inputs[\"gender\"]) # converting the gender column into dummy variables.\n",
467+
"\n",
468+
"display(dummies.head())\n",
469+
"print(dummies.dtypes)"
470+
]
471+
},
472+
{
473+
"cell_type": "code",
474+
"execution_count": 6,
475+
"id": "9bdf780c",
476+
"metadata": {},
477+
"outputs": [
478+
{
479+
"data": {
480+
"text/html": [
481+
"<div>\n",
482+
"<style scoped>\n",
483+
" .dataframe tbody tr th:only-of-type {\n",
484+
" vertical-align: middle;\n",
485+
" }\n",
486+
"\n",
487+
" .dataframe tbody tr th {\n",
488+
" vertical-align: top;\n",
489+
" }\n",
490+
"\n",
491+
" .dataframe thead th {\n",
492+
" text-align: right;\n",
493+
" }\n",
494+
"</style>\n",
495+
"<table border=\"1\" class=\"dataframe\">\n",
496+
" <thead>\n",
497+
" <tr style=\"text-align: right;\">\n",
498+
" <th></th>\n",
499+
" <th>p_class</th>\n",
500+
" <th>gender</th>\n",
501+
" <th>age</th>\n",
502+
" <th>fare</th>\n",
503+
" <th>female</th>\n",
504+
" <th>male</th>\n",
505+
" </tr>\n",
506+
" </thead>\n",
507+
" <tbody>\n",
508+
" <tr>\n",
509+
" <th>0</th>\n",
510+
" <td>3</td>\n",
511+
" <td>male</td>\n",
512+
" <td>22.0</td>\n",
513+
" <td>7.2500</td>\n",
514+
" <td>0</td>\n",
515+
" <td>1</td>\n",
516+
" </tr>\n",
517+
" <tr>\n",
518+
" <th>1</th>\n",
519+
" <td>1</td>\n",
520+
" <td>female</td>\n",
521+
" <td>38.0</td>\n",
522+
" <td>71.2833</td>\n",
523+
" <td>1</td>\n",
524+
" <td>0</td>\n",
525+
" </tr>\n",
526+
" <tr>\n",
527+
" <th>2</th>\n",
528+
" <td>3</td>\n",
529+
" <td>female</td>\n",
530+
" <td>26.0</td>\n",
531+
" <td>7.9250</td>\n",
532+
" <td>1</td>\n",
533+
" <td>0</td>\n",
534+
" </tr>\n",
535+
" <tr>\n",
536+
" <th>3</th>\n",
537+
" <td>1</td>\n",
538+
" <td>female</td>\n",
539+
" <td>35.0</td>\n",
540+
" <td>53.1000</td>\n",
541+
" <td>1</td>\n",
542+
" <td>0</td>\n",
543+
" </tr>\n",
544+
" <tr>\n",
545+
" <th>4</th>\n",
546+
" <td>3</td>\n",
547+
" <td>male</td>\n",
548+
" <td>35.0</td>\n",
549+
" <td>8.0500</td>\n",
550+
" <td>0</td>\n",
551+
" <td>1</td>\n",
552+
" </tr>\n",
553+
" </tbody>\n",
554+
"</table>\n",
555+
"</div>"
556+
],
557+
"text/plain": [
558+
" p_class gender age fare female male\n",
559+
"0 3 male 22.0 7.2500 0 1\n",
560+
"1 1 female 38.0 71.2833 1 0\n",
561+
"2 3 female 26.0 7.9250 1 0\n",
562+
"3 1 female 35.0 53.1000 1 0\n",
563+
"4 3 male 35.0 8.0500 0 1"
564+
]
565+
},
566+
"execution_count": 6,
567+
"metadata": {},
568+
"output_type": "execute_result"
569+
}
570+
],
571+
"source": [
572+
"# concatenating the inputs dataframe with the dummies dataframe.\n",
573+
"inputs = pd.concat([inputs, dummies], axis=1)\n",
574+
"inputs.head()"
575+
]
576+
},
577+
{
578+
"cell_type": "code",
579+
"execution_count": 7,
580+
"id": "24fcccc2",
581+
"metadata": {},
582+
"outputs": [
583+
{
584+
"data": {
585+
"text/html": [
586+
"<div>\n",
587+
"<style scoped>\n",
588+
" .dataframe tbody tr th:only-of-type {\n",
589+
" vertical-align: middle;\n",
590+
" }\n",
591+
"\n",
592+
" .dataframe tbody tr th {\n",
593+
" vertical-align: top;\n",
594+
" }\n",
595+
"\n",
596+
" .dataframe thead th {\n",
597+
" text-align: right;\n",
598+
" }\n",
599+
"</style>\n",
600+
"<table border=\"1\" class=\"dataframe\">\n",
601+
" <thead>\n",
602+
" <tr style=\"text-align: right;\">\n",
603+
" <th></th>\n",
604+
" <th>p_class</th>\n",
605+
" <th>age</th>\n",
606+
" <th>fare</th>\n",
607+
" <th>female</th>\n",
608+
" <th>male</th>\n",
609+
" </tr>\n",
610+
" </thead>\n",
611+
" <tbody>\n",
612+
" <tr>\n",
613+
" <th>0</th>\n",
614+
" <td>3</td>\n",
615+
" <td>22.0</td>\n",
616+
" <td>7.2500</td>\n",
617+
" <td>0</td>\n",
618+
" <td>1</td>\n",
619+
" </tr>\n",
620+
" <tr>\n",
621+
" <th>1</th>\n",
622+
" <td>1</td>\n",
623+
" <td>38.0</td>\n",
624+
" <td>71.2833</td>\n",
625+
" <td>1</td>\n",
626+
" <td>0</td>\n",
627+
" </tr>\n",
628+
" <tr>\n",
629+
" <th>2</th>\n",
630+
" <td>3</td>\n",
631+
" <td>26.0</td>\n",
632+
" <td>7.9250</td>\n",
633+
" <td>1</td>\n",
634+
" <td>0</td>\n",
635+
" </tr>\n",
636+
" <tr>\n",
637+
" <th>3</th>\n",
638+
" <td>1</td>\n",
639+
" <td>35.0</td>\n",
640+
" <td>53.1000</td>\n",
641+
" <td>1</td>\n",
642+
" <td>0</td>\n",
643+
" </tr>\n",
644+
" <tr>\n",
645+
" <th>4</th>\n",
646+
" <td>3</td>\n",
647+
" <td>35.0</td>\n",
648+
" <td>8.0500</td>\n",
649+
" <td>0</td>\n",
650+
" <td>1</td>\n",
651+
" </tr>\n",
652+
" </tbody>\n",
653+
"</table>\n",
654+
"</div>"
655+
],
656+
"text/plain": [
657+
" p_class age fare female male\n",
658+
"0 3 22.0 7.2500 0 1\n",
659+
"1 1 38.0 71.2833 1 0\n",
660+
"2 3 26.0 7.9250 1 0\n",
661+
"3 1 35.0 53.1000 1 0\n",
662+
"4 3 35.0 8.0500 0 1"
663+
]
664+
},
665+
"execution_count": 7,
666+
"metadata": {},
667+
"output_type": "execute_result"
668+
}
669+
],
670+
"source": [
671+
"# dropping the gender column because we now have the female and male columns.\n",
672+
"inputs.drop([\"gender\"], axis=1, inplace=True)\n",
673+
"inputs.head()"
674+
]
675+
},
676+
{
677+
"cell_type": "code",
678+
"execution_count": 8,
679+
"id": "c8f8c764",
680+
"metadata": {},
681+
"outputs": [
682+
{
683+
"data": {
684+
"text/plain": [
685+
"0 22.0\n",
686+
"1 38.0\n",
687+
"2 26.0\n",
688+
"3 35.0\n",
689+
"4 35.0\n",
690+
"5 NaN\n",
691+
"6 54.0\n",
692+
"7 2.0\n",
693+
"8 27.0\n",
694+
"9 14.0\n",
695+
"Name: age, dtype: float64"
696+
]
697+
},
698+
"execution_count": 8,
699+
"metadata": {},
700+
"output_type": "execute_result"
701+
}
702+
],
703+
"source": [
704+
"# it can be observed that some columns contains null values.\n",
705+
"inputs.age[:10]"
706+
]
707+
},
708+
{
709+
"cell_type": "code",
710+
"execution_count": 9,
711+
"id": "c9c01a43",
712+
"metadata": {},
713+
"outputs": [
714+
{
715+
"data": {
716+
"text/plain": [
717+
"0 22.000000\n",
718+
"1 38.000000\n",
719+
"2 26.000000\n",
720+
"3 35.000000\n",
721+
"4 35.000000\n",
722+
"5 29.699118\n",
723+
"6 54.000000\n",
724+
"7 2.000000\n",
725+
"8 27.000000\n",
726+
"9 14.000000\n",
727+
"Name: age, dtype: float64"
728+
]
729+
},
730+
"execution_count": 9,
731+
"metadata": {},
732+
"output_type": "execute_result"
733+
}
734+
],
735+
"source": [
736+
"# one way of handling these null values is to fill those values with the mean value of the whole column.\n",
737+
"# we can also make these values an integer type values.\n",
738+
"inputs[\"age\"] = inputs[\"age\"].fillna(inputs[\"age\"].mean())\n",
739+
"\n",
740+
"inputs.age[:10]\n",
741+
"# as we can see the 5th row in the earlier cell was null and now it is replaced with the mean value."
742+
]
743+
},
744+
{
745+
"cell_type": "code",
746+
"execution_count": 10,
747+
"id": "5bda4746",
748+
"metadata": {},
749+
"outputs": [
750+
{
751+
"name": "stdout",
752+
"output_type": "stream",
753+
"text": [
754+
"712 179 891\n",
755+
"0.7991021324354658\n",
756+
"0.20089786756453423\n"
757+
]
758+
}
759+
],
760+
"source": [
761+
"X_train, X_test, y_train, y_test = train_test_split(inputs, target, test_size=0.2)\n",
762+
"# 20% test size and 80% train size.\n",
763+
"print(len(X_train), len(X_test), len(inputs))\n",
764+
"\n",
765+
"# calculating training and testing data percentage.\n",
766+
"print(len(X_train) / len(inputs)) # training data %\n",
767+
"print(len(X_test) / len(inputs)) # testing data %"
768+
]
769+
},
770+
{
771+
"cell_type": "code",
772+
"execution_count": 11,
773+
"id": "42deb68a",
774+
"metadata": {},
775+
"outputs": [
776+
{
777+
"data": {
778+
"text/html": [
779+
"<style>#sk-container-id-1 {color: black;background-color: white;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-1 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-1 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-1 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>GaussianNB()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">GaussianNB</label><div class=\"sk-toggleable__content\"><pre>GaussianNB()</pre></div></div></div></div></div>"
780+
],
781+
"text/plain": [
782+
"GaussianNB()"
783+
]
784+
},
785+
"execution_count": 11,
786+
"metadata": {},
787+
"output_type": "execute_result"
788+
}
789+
],
790+
"source": [
791+
"# we are using the Gaussian Naive Bayes model.\n",
792+
"model = GaussianNB()\n",
793+
"model.fit(X_train, y_train)"
794+
]
795+
},
796+
{
797+
"cell_type": "code",
798+
"execution_count": 12,
799+
"id": "422daf07",
800+
"metadata": {},
801+
"outputs": [
802+
{
803+
"data": {
804+
"text/plain": [
805+
"0.7374301675977654"
806+
]
807+
},
808+
"execution_count": 12,
809+
"metadata": {},
810+
"output_type": "execute_result"
811+
}
812+
],
813+
"source": [
814+
"model.score(X_test, y_test)"
815+
]
816+
},
817+
{
818+
"cell_type": "code",
819+
"execution_count": 13,
820+
"id": "ec58fa13",
821+
"metadata": {},
822+
"outputs": [
823+
{
824+
"name": "stdout",
825+
"output_type": "stream",
826+
"text": [
827+
"[0 0 1 0 0]\n",
828+
"0.9931484209536514, 0.015823706167673823, 0.9932294253552363, 0.9833500719459427, 0.9919031866574911, "
829+
]
830+
}
831+
],
832+
"source": [
833+
"pred = np.array(model.predict(X_test))\n",
834+
"pred_probability = np.array(model.predict_proba(X_test)) # calculating the probabilities\n",
835+
"\n",
836+
"print(pred[:5])\n",
837+
"for i in range(1, 6):\n",
838+
" print(pred_probability[i][0], end=\", \")"
839+
]
840+
},
841+
{
842+
"cell_type": "code",
843+
"execution_count": null,
844+
"id": "25eed843",
845+
"metadata": {},
846+
"outputs": [],
847+
"source": []
848+
}
849+
],
850+
"metadata": {
851+
"kernelspec": {
852+
"display_name": "Python 3 (ipykernel)",
853+
"language": "python",
854+
"name": "python3"
855+
},
856+
"language_info": {
857+
"codemirror_mode": {
858+
"name": "ipython",
859+
"version": 3
860+
},
861+
"file_extension": ".py",
862+
"mimetype": "text/x-python",
863+
"name": "python",
864+
"nbconvert_exporter": "python",
865+
"pygments_lexer": "ipython3",
866+
"version": "3.11.2"
867+
}
868+
},
869+
"nbformat": 4,
870+
"nbformat_minor": 5
871+
}

0 commit comments

Comments
 (0)
Please sign in to comment.