Spaces:
Sleeping
Sleeping
ryantrisnadi
commited on
Commit
•
55f8f0c
1
Parent(s):
9af275a
Upload 2 files
Browse files- P1M2_Ryan_Trisnadi.ipynb +0 -0
- P1M2_Ryan_Trisnadi_inf.ipynb +318 -0
P1M2_Ryan_Trisnadi.ipynb
ADDED
The diff for this file is too large to render.
See raw diff
|
|
P1M2_Ryan_Trisnadi_inf.ipynb
ADDED
@@ -0,0 +1,318 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cells": [
|
3 |
+
{
|
4 |
+
"cell_type": "code",
|
5 |
+
"execution_count": 1,
|
6 |
+
"metadata": {},
|
7 |
+
"outputs": [
|
8 |
+
{
|
9 |
+
"name": "stderr",
|
10 |
+
"output_type": "stream",
|
11 |
+
"text": [
|
12 |
+
"/opt/miniconda3/lib/python3.12/site-packages/threadpoolctl.py:1214: RuntimeWarning: \n",
|
13 |
+
"Found Intel OpenMP ('libiomp') and LLVM OpenMP ('libomp') loaded at\n",
|
14 |
+
"the same time. Both libraries are known to be incompatible and this\n",
|
15 |
+
"can cause random crashes or deadlocks on Linux when loaded in the\n",
|
16 |
+
"same Python program.\n",
|
17 |
+
"Using threadpoolctl may cause crashes or deadlocks. For more\n",
|
18 |
+
"information and possible workarounds, please see\n",
|
19 |
+
" https://github.com/joblib/threadpoolctl/blob/master/multiple_openmp.md\n",
|
20 |
+
"\n",
|
21 |
+
" warnings.warn(msg, RuntimeWarning)\n"
|
22 |
+
]
|
23 |
+
}
|
24 |
+
],
|
25 |
+
"source": [
|
26 |
+
"import json\n",
|
27 |
+
"import pickle\n",
|
28 |
+
"\n",
|
29 |
+
"# Load the saved list of numerical columns\n",
|
30 |
+
"with open('list_num_cols.txt', 'r') as file_1:\n",
|
31 |
+
" combined_columns = json.load(file_1)\n",
|
32 |
+
"\n",
|
33 |
+
"# Load the saved model\n",
|
34 |
+
"with open('model.pkl', 'rb') as file_2:\n",
|
35 |
+
" lr = pickle.load(file_2)"
|
36 |
+
]
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"cell_type": "markdown",
|
40 |
+
"metadata": {},
|
41 |
+
"source": [
|
42 |
+
"Kita akan coba buka yang kita tadi save untuk dipake untuk inference."
|
43 |
+
]
|
44 |
+
},
|
45 |
+
{
|
46 |
+
"cell_type": "code",
|
47 |
+
"execution_count": 2,
|
48 |
+
"metadata": {},
|
49 |
+
"outputs": [
|
50 |
+
{
|
51 |
+
"name": "stdout",
|
52 |
+
"output_type": "stream",
|
53 |
+
"text": [
|
54 |
+
"Original Dummy Data:\n",
|
55 |
+
" Suburb Rooms Price Distance Bathroom Car Landsize \\\n",
|
56 |
+
"0 Abbotsford 2 1035000.0 2.5 1.0 0.0 156.0 \n",
|
57 |
+
"1 Abbotsford 3 1465000.0 2.5 2.0 0.0 134.0 \n",
|
58 |
+
"2 Abbotsford 4 1600000.0 2.5 1.0 2.0 120.0 \n",
|
59 |
+
"3 Abbotsford 3 1876000.0 2.5 2.0 0.0 245.0 \n",
|
60 |
+
"4 Abbotsford 2 1636000.0 2.5 1.0 2.0 256.0 \n",
|
61 |
+
"\n",
|
62 |
+
" BuildingArea YearBuilt Propertycount \n",
|
63 |
+
"0 79.0 1900.0 4019.0 \n",
|
64 |
+
"1 150.0 1900.0 4019.0 \n",
|
65 |
+
"2 142.0 2014.0 4019.0 \n",
|
66 |
+
"3 210.0 1910.0 4019.0 \n",
|
67 |
+
"4 107.0 1890.0 4019.0 \n"
|
68 |
+
]
|
69 |
+
}
|
70 |
+
],
|
71 |
+
"source": [
|
72 |
+
"import pandas as pd\n",
|
73 |
+
"\n",
|
74 |
+
"# Assuming df_data_dummy is your DataFrame with the data\n",
|
75 |
+
"df_data_dummy = pd.DataFrame({\n",
|
76 |
+
"\n",
|
77 |
+
" \"Suburb\": [\"Abbotsford\", \"Abbotsford\", \"Abbotsford\", \"Abbotsford\", \"Abbotsford\"],\n",
|
78 |
+
" \"Rooms\": [2, 3, 4, 3, 2],\n",
|
79 |
+
" \"Price\": [1035000.0, 1465000.0, 1600000.0, 1876000.0, 1636000.0],\n",
|
80 |
+
" \"Distance\": [2.5, 2.5, 2.5, 2.5, 2.5],\n",
|
81 |
+
" \"Bathroom\": [1.0, 2.0, 1.0, 2.0, 1.0],\n",
|
82 |
+
" \"Car\": [0.0, 0.0, 2.0, 0.0, 2.0],\n",
|
83 |
+
" \"Landsize\": [156.0, 134.0, 120.0, 245.0, 256.0],\n",
|
84 |
+
" \"BuildingArea\": [79.0, 150.0, 142.0, 210.0, 107.0],\n",
|
85 |
+
" \"YearBuilt\": [1900.0, 1900.0, 2014.0, 1910.0, 1890.0],\n",
|
86 |
+
" \"Propertycount\": [4019.0, 4019.0, 4019.0, 4019.0, 4019.0]\n",
|
87 |
+
"\n",
|
88 |
+
"})\n",
|
89 |
+
"\n",
|
90 |
+
"df_dummy_data = pd.DataFrame(df_data_dummy)\n",
|
91 |
+
"print(\"Original Dummy Data:\")\n",
|
92 |
+
"print(df_dummy_data)\n",
|
93 |
+
"\n"
|
94 |
+
]
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"cell_type": "markdown",
|
98 |
+
"metadata": {},
|
99 |
+
"source": [
|
100 |
+
"Kita akan membuat dataset \"dummy\" baru dan masukan ke dataframe dinamakan \"df_dummy_data\". Kita mau uji nanti dengan linear regression."
|
101 |
+
]
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"cell_type": "code",
|
105 |
+
"execution_count": 3,
|
106 |
+
"metadata": {},
|
107 |
+
"outputs": [
|
108 |
+
{
|
109 |
+
"data": {
|
110 |
+
"text/html": [
|
111 |
+
"<div>\n",
|
112 |
+
"<style scoped>\n",
|
113 |
+
" .dataframe tbody tr th:only-of-type {\n",
|
114 |
+
" vertical-align: middle;\n",
|
115 |
+
" }\n",
|
116 |
+
"\n",
|
117 |
+
" .dataframe tbody tr th {\n",
|
118 |
+
" vertical-align: top;\n",
|
119 |
+
" }\n",
|
120 |
+
"\n",
|
121 |
+
" .dataframe thead th {\n",
|
122 |
+
" text-align: right;\n",
|
123 |
+
" }\n",
|
124 |
+
"</style>\n",
|
125 |
+
"<table border=\"1\" class=\"dataframe\">\n",
|
126 |
+
" <thead>\n",
|
127 |
+
" <tr style=\"text-align: right;\">\n",
|
128 |
+
" <th></th>\n",
|
129 |
+
" <th>Suburb</th>\n",
|
130 |
+
" <th>Rooms</th>\n",
|
131 |
+
" <th>Price</th>\n",
|
132 |
+
" <th>Distance</th>\n",
|
133 |
+
" <th>Bathroom</th>\n",
|
134 |
+
" <th>Car</th>\n",
|
135 |
+
" <th>Landsize</th>\n",
|
136 |
+
" <th>BuildingArea</th>\n",
|
137 |
+
" <th>YearBuilt</th>\n",
|
138 |
+
" <th>Propertycount</th>\n",
|
139 |
+
" </tr>\n",
|
140 |
+
" </thead>\n",
|
141 |
+
" <tbody>\n",
|
142 |
+
" <tr>\n",
|
143 |
+
" <th>0</th>\n",
|
144 |
+
" <td>Abbotsford</td>\n",
|
145 |
+
" <td>2</td>\n",
|
146 |
+
" <td>1035000.0</td>\n",
|
147 |
+
" <td>2.5</td>\n",
|
148 |
+
" <td>1.0</td>\n",
|
149 |
+
" <td>0.0</td>\n",
|
150 |
+
" <td>156.0</td>\n",
|
151 |
+
" <td>79.0</td>\n",
|
152 |
+
" <td>1900.0</td>\n",
|
153 |
+
" <td>4019.0</td>\n",
|
154 |
+
" </tr>\n",
|
155 |
+
" <tr>\n",
|
156 |
+
" <th>1</th>\n",
|
157 |
+
" <td>Abbotsford</td>\n",
|
158 |
+
" <td>3</td>\n",
|
159 |
+
" <td>1465000.0</td>\n",
|
160 |
+
" <td>2.5</td>\n",
|
161 |
+
" <td>2.0</td>\n",
|
162 |
+
" <td>0.0</td>\n",
|
163 |
+
" <td>134.0</td>\n",
|
164 |
+
" <td>150.0</td>\n",
|
165 |
+
" <td>1900.0</td>\n",
|
166 |
+
" <td>4019.0</td>\n",
|
167 |
+
" </tr>\n",
|
168 |
+
" <tr>\n",
|
169 |
+
" <th>2</th>\n",
|
170 |
+
" <td>Abbotsford</td>\n",
|
171 |
+
" <td>4</td>\n",
|
172 |
+
" <td>1600000.0</td>\n",
|
173 |
+
" <td>2.5</td>\n",
|
174 |
+
" <td>1.0</td>\n",
|
175 |
+
" <td>2.0</td>\n",
|
176 |
+
" <td>120.0</td>\n",
|
177 |
+
" <td>142.0</td>\n",
|
178 |
+
" <td>2014.0</td>\n",
|
179 |
+
" <td>4019.0</td>\n",
|
180 |
+
" </tr>\n",
|
181 |
+
" <tr>\n",
|
182 |
+
" <th>3</th>\n",
|
183 |
+
" <td>Abbotsford</td>\n",
|
184 |
+
" <td>3</td>\n",
|
185 |
+
" <td>1876000.0</td>\n",
|
186 |
+
" <td>2.5</td>\n",
|
187 |
+
" <td>2.0</td>\n",
|
188 |
+
" <td>0.0</td>\n",
|
189 |
+
" <td>245.0</td>\n",
|
190 |
+
" <td>210.0</td>\n",
|
191 |
+
" <td>1910.0</td>\n",
|
192 |
+
" <td>4019.0</td>\n",
|
193 |
+
" </tr>\n",
|
194 |
+
" <tr>\n",
|
195 |
+
" <th>4</th>\n",
|
196 |
+
" <td>Abbotsford</td>\n",
|
197 |
+
" <td>2</td>\n",
|
198 |
+
" <td>1636000.0</td>\n",
|
199 |
+
" <td>2.5</td>\n",
|
200 |
+
" <td>1.0</td>\n",
|
201 |
+
" <td>2.0</td>\n",
|
202 |
+
" <td>256.0</td>\n",
|
203 |
+
" <td>107.0</td>\n",
|
204 |
+
" <td>1890.0</td>\n",
|
205 |
+
" <td>4019.0</td>\n",
|
206 |
+
" </tr>\n",
|
207 |
+
" </tbody>\n",
|
208 |
+
"</table>\n",
|
209 |
+
"</div>"
|
210 |
+
],
|
211 |
+
"text/plain": [
|
212 |
+
" Suburb Rooms Price Distance Bathroom Car Landsize \\\n",
|
213 |
+
"0 Abbotsford 2 1035000.0 2.5 1.0 0.0 156.0 \n",
|
214 |
+
"1 Abbotsford 3 1465000.0 2.5 2.0 0.0 134.0 \n",
|
215 |
+
"2 Abbotsford 4 1600000.0 2.5 1.0 2.0 120.0 \n",
|
216 |
+
"3 Abbotsford 3 1876000.0 2.5 2.0 0.0 245.0 \n",
|
217 |
+
"4 Abbotsford 2 1636000.0 2.5 1.0 2.0 256.0 \n",
|
218 |
+
"\n",
|
219 |
+
" BuildingArea YearBuilt Propertycount \n",
|
220 |
+
"0 79.0 1900.0 4019.0 \n",
|
221 |
+
"1 150.0 1900.0 4019.0 \n",
|
222 |
+
"2 142.0 2014.0 4019.0 \n",
|
223 |
+
"3 210.0 1910.0 4019.0 \n",
|
224 |
+
"4 107.0 1890.0 4019.0 "
|
225 |
+
]
|
226 |
+
},
|
227 |
+
"execution_count": 3,
|
228 |
+
"metadata": {},
|
229 |
+
"output_type": "execute_result"
|
230 |
+
}
|
231 |
+
],
|
232 |
+
"source": [
|
233 |
+
"df_dummy_data"
|
234 |
+
]
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"cell_type": "code",
|
238 |
+
"execution_count": 4,
|
239 |
+
"metadata": {},
|
240 |
+
"outputs": [],
|
241 |
+
"source": [
|
242 |
+
"df_dummy_data_new = df_dummy_data[combined_columns]"
|
243 |
+
]
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"cell_type": "markdown",
|
247 |
+
"metadata": {},
|
248 |
+
"source": [
|
249 |
+
"masukan kolom ke data dummy. Berikutnya namakan variable baru."
|
250 |
+
]
|
251 |
+
},
|
252 |
+
{
|
253 |
+
"cell_type": "code",
|
254 |
+
"execution_count": 5,
|
255 |
+
"metadata": {},
|
256 |
+
"outputs": [],
|
257 |
+
"source": [
|
258 |
+
"predictions = lr.predict(df_dummy_data_new)"
|
259 |
+
]
|
260 |
+
},
|
261 |
+
{
|
262 |
+
"cell_type": "markdown",
|
263 |
+
"metadata": {},
|
264 |
+
"source": [
|
265 |
+
"Akan membuat prediksi dengan linear regression di test. "
|
266 |
+
]
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"cell_type": "code",
|
270 |
+
"execution_count": 6,
|
271 |
+
"metadata": {},
|
272 |
+
"outputs": [
|
273 |
+
{
|
274 |
+
"data": {
|
275 |
+
"text/plain": [
|
276 |
+
"array([1101277.02454045, 1665725.95948649, 1297970.1974852 ,\n",
|
277 |
+
" 1639455.71625785, 1297855.42299958])"
|
278 |
+
]
|
279 |
+
},
|
280 |
+
"execution_count": 6,
|
281 |
+
"metadata": {},
|
282 |
+
"output_type": "execute_result"
|
283 |
+
}
|
284 |
+
],
|
285 |
+
"source": [
|
286 |
+
"predictions"
|
287 |
+
]
|
288 |
+
},
|
289 |
+
{
|
290 |
+
"cell_type": "markdown",
|
291 |
+
"metadata": {},
|
292 |
+
"source": [
|
293 |
+
"Keluarlah prediksi harga rumah di beberapa bulan kedepan. Harganya semua diatas AU$1 Juta."
|
294 |
+
]
|
295 |
+
}
|
296 |
+
],
|
297 |
+
"metadata": {
|
298 |
+
"kernelspec": {
|
299 |
+
"display_name": "base",
|
300 |
+
"language": "python",
|
301 |
+
"name": "python3"
|
302 |
+
},
|
303 |
+
"language_info": {
|
304 |
+
"codemirror_mode": {
|
305 |
+
"name": "ipython",
|
306 |
+
"version": 3
|
307 |
+
},
|
308 |
+
"file_extension": ".py",
|
309 |
+
"mimetype": "text/x-python",
|
310 |
+
"name": "python",
|
311 |
+
"nbconvert_exporter": "python",
|
312 |
+
"pygments_lexer": "ipython3",
|
313 |
+
"version": "3.12.2"
|
314 |
+
}
|
315 |
+
},
|
316 |
+
"nbformat": 4,
|
317 |
+
"nbformat_minor": 2
|
318 |
+
}
|