Skip to content

Commit d5b6c90

Browse files
PyDataBlogPyDataBlog
authored
Added julia ex2 files
Added files needed to reproduce the regularized logistic regression exercise
1 parent d99ab0d commit d5b6c90

File tree

8 files changed

+55042
-0
lines changed

8 files changed

+55042
-0
lines changed

‎Tutorials/HTRU2_julia_project/HTRU_2.csv‎

Lines changed: 17899 additions & 0 deletions
Large diffs are not rendered by default.

‎Tutorials/HTRU2_julia_project/X_test.csv‎

Lines changed: 3581 additions & 0 deletions
Large diffs are not rendered by default.

‎Tutorials/HTRU2_julia_project/X_train.csv‎

Lines changed: 14319 additions & 0 deletions
Large diffs are not rendered by default.

‎Tutorials/HTRU2_julia_project/sklearn_implementation.ipynb‎

Lines changed: 301 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,301 @@
1+
{
2+
"cells": [
3+
{
4+
"cell_type": "code",
5+
"source": [
6+
"# Import needed libraries\n",
7+
"import numpy as np\n",
8+
"from sklearn.preprocessing import StandardScaler\n",
9+
"from sklearn.pipeline import Pipeline\n",
10+
"from sklearn.linear_model import SGDClassifier"
11+
],
12+
"outputs": [],
13+
"execution_count": 1,
14+
"metadata": {}
15+
},
16+
{
17+
"cell_type": "code",
18+
"source": [
19+
"# Read data\n",
20+
"X_train = np.genfromtxt('X_train.csv', delimiter=',', skip_header=1)\n",
21+
"X_test = np.genfromtxt('X_test.csv', delimiter=',', skip_header=1)\n",
22+
"y_train = np.genfromtxt('y_train.csv', delimiter=',', skip_header=1)\n",
23+
"y_test = np.genfromtxt('y_test.csv', delimiter=',', skip_header=1)"
24+
],
25+
"outputs": [],
26+
"execution_count": 2,
27+
"metadata": {}
28+
},
29+
{
30+
"cell_type": "code",
31+
"source": [
32+
"classifiers = [\n",
33+
" SGDClassifier(penalty='l2', loss='log', alpha=0.0001)\n",
34+
"]"
35+
],
36+
"outputs": [],
37+
"execution_count": 4,
38+
"metadata": {
39+
"collapsed": false,
40+
"jupyter": {
41+
"source_hidden": false,
42+
"outputs_hidden": false
43+
},
44+
"nteract": {
45+
"transient": {
46+
"deleting": false
47+
}
48+
}
49+
}
50+
},
51+
{
52+
"cell_type": "code",
53+
"source": [],
54+
"outputs": [],
55+
"execution_count": 4,
56+
"metadata": {
57+
"collapsed": false,
58+
"jupyter": {
59+
"source_hidden": false,
60+
"outputs_hidden": false
61+
},
62+
"nteract": {
63+
"transient": {
64+
"deleting": false
65+
}
66+
}
67+
}
68+
},
69+
{
70+
"cell_type": "code",
71+
"source": [
72+
"def score_model(X_train, y_train, X_test, y_test, model):\n",
73+
" model = Pipeline(steps=[\n",
74+
" ('scale_x', StandardScaler()),\n",
75+
" ('clf', model)\n",
76+
" ])\n",
77+
" \n",
78+
" model_name = model.named_steps['clf'].__class__.__name__\n",
79+
" \n",
80+
" model.fit(X_train, y_train)\n",
81+
" \n",
82+
" print(f'Train score for {model_name}: ', round(model.score(X_train, y_train), 4))\n",
83+
" print(f'Test score for {model_name}: ', round(model.score(X_test, y_test), 4))\n",
84+
" print()"
85+
],
86+
"outputs": [],
87+
"execution_count": 5,
88+
"metadata": {
89+
"collapsed": false,
90+
"jupyter": {
91+
"source_hidden": false,
92+
"outputs_hidden": false
93+
},
94+
"nteract": {
95+
"transient": {
96+
"deleting": false
97+
}
98+
}
99+
}
100+
},
101+
{
102+
"cell_type": "code",
103+
"source": [],
104+
"outputs": [],
105+
"execution_count": 5,
106+
"metadata": {
107+
"collapsed": false,
108+
"jupyter": {
109+
"source_hidden": false,
110+
"outputs_hidden": false
111+
},
112+
"nteract": {
113+
"transient": {
114+
"deleting": false
115+
}
116+
}
117+
}
118+
},
119+
{
120+
"cell_type": "code",
121+
"source": [
122+
"for clf in classifiers:\n",
123+
" score_model(X_train, y_train, X_test, y_test, clf)"
124+
],
125+
"outputs": [
126+
{
127+
"output_type": "stream",
128+
"name": "stdout",
129+
"text": [
130+
"Train score for SGDClassifier: 0.9791\n",
131+
"Test score for SGDClassifier: 0.9807\n",
132+
"\n"
133+
]
134+
}
135+
],
136+
"execution_count": 6,
137+
"metadata": {
138+
"collapsed": false,
139+
"jupyter": {
140+
"source_hidden": false,
141+
"outputs_hidden": false
142+
},
143+
"nteract": {
144+
"transient": {
145+
"deleting": false
146+
}
147+
}
148+
}
149+
},
150+
{
151+
"cell_type": "code",
152+
"source": [],
153+
"outputs": [],
154+
"execution_count": null,
155+
"metadata": {
156+
"collapsed": false,
157+
"jupyter": {
158+
"source_hidden": false,
159+
"outputs_hidden": false
160+
},
161+
"nteract": {
162+
"transient": {
163+
"deleting": false
164+
}
165+
}
166+
}
167+
},
168+
{
169+
"cell_type": "code",
170+
"source": [],
171+
"outputs": [],
172+
"execution_count": null,
173+
"metadata": {
174+
"collapsed": false,
175+
"jupyter": {
176+
"source_hidden": false,
177+
"outputs_hidden": false
178+
},
179+
"nteract": {
180+
"transient": {
181+
"deleting": false
182+
}
183+
}
184+
}
185+
},
186+
{
187+
"cell_type": "code",
188+
"source": [],
189+
"outputs": [],
190+
"execution_count": null,
191+
"metadata": {
192+
"collapsed": false,
193+
"jupyter": {
194+
"source_hidden": false,
195+
"outputs_hidden": false
196+
},
197+
"nteract": {
198+
"transient": {
199+
"deleting": false
200+
}
201+
}
202+
}
203+
},
204+
{
205+
"cell_type": "code",
206+
"source": [],
207+
"outputs": [],
208+
"execution_count": null,
209+
"metadata": {
210+
"collapsed": false,
211+
"jupyter": {
212+
"source_hidden": false,
213+
"outputs_hidden": false
214+
},
215+
"nteract": {
216+
"transient": {
217+
"deleting": false
218+
}
219+
}
220+
}
221+
},
222+
{
223+
"cell_type": "code",
224+
"source": [],
225+
"outputs": [],
226+
"execution_count": null,
227+
"metadata": {
228+
"collapsed": false,
229+
"jupyter": {
230+
"source_hidden": false,
231+
"outputs_hidden": false
232+
},
233+
"nteract": {
234+
"transient": {
235+
"deleting": false
236+
}
237+
}
238+
}
239+
},
240+
{
241+
"cell_type": "code",
242+
"source": [],
243+
"outputs": [],
244+
"execution_count": null,
245+
"metadata": {
246+
"collapsed": false,
247+
"jupyter": {
248+
"source_hidden": false,
249+
"outputs_hidden": false
250+
},
251+
"nteract": {
252+
"transient": {
253+
"deleting": false
254+
}
255+
}
256+
}
257+
},
258+
{
259+
"cell_type": "code",
260+
"source": [],
261+
"outputs": [],
262+
"execution_count": null,
263+
"metadata": {
264+
"collapsed": false,
265+
"jupyter": {
266+
"source_hidden": false,
267+
"outputs_hidden": false
268+
},
269+
"nteract": {
270+
"transient": {
271+
"deleting": false
272+
}
273+
}
274+
}
275+
}
276+
],
277+
"metadata": {
278+
"kernelspec": {
279+
"display_name": "Python 3",
280+
"language": "python",
281+
"name": "python3"
282+
},
283+
"language_info": {
284+
"name": "python",
285+
"version": "3.7.6",
286+
"mimetype": "text/x-python",
287+
"codemirror_mode": {
288+
"name": "ipython",
289+
"version": 3
290+
},
291+
"pygments_lexer": "ipython3",
292+
"nbconvert_exporter": "python",
293+
"file_extension": ".py"
294+
},
295+
"nteract": {
296+
"version": "0.21.0"
297+
}
298+
},
299+
"nbformat": 4,
300+
"nbformat_minor": 4
301+
}

0 commit comments

Comments
 (0)