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 "/home/m/.local/lib/python3.7/site-packages/tensorflow/python/framework/dtypes.py:516: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
13 " _np_qint8 = np.dtype([(\"qint8\", np.int8, 1)])\n",
14 "/home/m/.local/lib/python3.7/site-packages/tensorflow/python/framework/dtypes.py:517: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
15 " _np_quint8 = np.dtype([(\"quint8\", np.uint8, 1)])\n",
16 "/home/m/.local/lib/python3.7/site-packages/tensorflow/python/framework/dtypes.py:518: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
17 " _np_qint16 = np.dtype([(\"qint16\", np.int16, 1)])\n",
18 "/home/m/.local/lib/python3.7/site-packages/tensorflow/python/framework/dtypes.py:519: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
19 " _np_quint16 = np.dtype([(\"quint16\", np.uint16, 1)])\n",
20 "/home/m/.local/lib/python3.7/site-packages/tensorflow/python/framework/dtypes.py:520: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
21 " _np_qint32 = np.dtype([(\"qint32\", np.int32, 1)])\n",
22 "/home/m/.local/lib/python3.7/site-packages/tensorflow/python/framework/dtypes.py:525: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
23 " np_resource = np.dtype([(\"resource\", np.ubyte, 1)])\n"
24 ]
25 },
26 {
27 "name": "stdout",
28 "output_type": "stream",
29 "text": [
30 "2.0.0-beta1\n"
31 ]
32 },
33 {
34 "name": "stderr",
35 "output_type": "stream",
36 "text": [
37 "/home/m/.local/lib/python3.7/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:541: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
38 " _np_qint8 = np.dtype([(\"qint8\", np.int8, 1)])\n",
39 "/home/m/.local/lib/python3.7/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:542: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
40 " _np_quint8 = np.dtype([(\"quint8\", np.uint8, 1)])\n",
41 "/home/m/.local/lib/python3.7/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:543: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
42 " _np_qint16 = np.dtype([(\"qint16\", np.int16, 1)])\n",
43 "/home/m/.local/lib/python3.7/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:544: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
44 " _np_quint16 = np.dtype([(\"quint16\", np.uint16, 1)])\n",
45 "/home/m/.local/lib/python3.7/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:545: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
46 " _np_qint32 = np.dtype([(\"qint32\", np.int32, 1)])\n",
47 "/home/m/.local/lib/python3.7/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:550: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
48 " np_resource = np.dtype([(\"resource\", np.ubyte, 1)])\n"
49 ]
50 }
51 ],
52 "source": [
53 "import tensorflow as tf\n",
54 "from tensorflow import keras\n",
55 "\n",
56 "# Helper libraries\n",
57 "import numpy as np\n",
58 "import matplotlib.pyplot as plt\n",
59 "\n",
60 "print(tf.__version__)"
61 ]
62 },
63 {
64 "cell_type": "code",
65 "execution_count": 2,
66 "metadata": {},
67 "outputs": [],
68 "source": [
69 "from numpy import genfromtxt\n",
70 "data = genfromtxt('data.csv', delimiter=',')"
71 ]
72 },
73 {
74 "cell_type": "code",
75 "execution_count": 3,
76 "metadata": {},
77 "outputs": [],
78 "source": [
79 "data_input = data[:,0:3]\n",
80 "data_labels = data[:,3]\n",
81 "\n",
82 "#data_input = np.transpose(data_input)\n",
83 "#data_labels = np.transpose(data_labels)"
84 ]
85 },
86 {
87 "cell_type": "code",
88 "execution_count": 4,
89 "metadata": {},
90 "outputs": [
91 {
92 "name": "stdout",
93 "output_type": "stream",
94 "text": [
95 "(600, 3)\n",
96 "[1.e-01 1.e+00 3.e+02]\n"
97 ]
98 }
99 ],
100 "source": [
101 "print(np.shape(data_input))\n",
102 "print(data_input[2])"
103 ]
104 },
105 {
106 "cell_type": "markdown",
107 "metadata": {},
108 "source": [
109 "print(len(data_input))\n",
110 "print(len(data_labels))"
111 ]
112 },
113 {
114 "cell_type": "code",
115 "execution_count": 5,
116 "metadata": {},
117 "outputs": [
118 {
119 "name": "stdout",
120 "output_type": "stream",
121 "text": [
122 "(500, 3)\n",
123 "(100, 3)\n",
124 "(500,)\n",
125 "(100,)\n"
126 ]
127 }
128 ],
129 "source": [
130 "data_input_train = data_input[0:500,:]\n",
131 "data_input_test = data_input[500:,:]\n",
132 "\n",
133 "data_labels_train = data_labels[0:500]\n",
134 "data_labels_test = data_labels[500:]\n",
135 "\n",
136 "print(np.shape(data_input_train))\n",
137 "print(np.shape(data_input_test))\n",
138 "\n",
139 "print(np.shape(data_labels_train))\n",
140 "print(np.shape(data_labels_test))"
141 ]
142 },
143 {
144 "cell_type": "code",
145 "execution_count": 6,
146 "metadata": {},
147 "outputs": [],
148 "source": [
149 "model = keras.Sequential([\n",
150 " keras.layers.Dense(128, activation='relu', input_shape=[3]),\n",
151 " keras.layers.Dense(512, activation='relu'),\n",
152 " keras.layers.Dense(512, activation='relu'),\n",
153 " keras.layers.Dense(512, activation='relu'),\n",
154 " keras.layers.Dense(128, activation='relu'),\n",
155 " keras.layers.Dense(1)\n",
156 "])"
157 ]
158 },
159 {
160 "cell_type": "code",
161 "execution_count": 7,
162 "metadata": {},
163 "outputs": [],
164 "source": [
165 "optimizer = tf.keras.optimizers.RMSprop(0.001)\n",
166 "model.compile(loss='mse',\n",
167 " optimizer=optimizer,\n",
168 " metrics=['accuracy'])"
169 ]
170 },
171 {
172 "cell_type": "code",
173 "execution_count": 8,
174 "metadata": {},
175 "outputs": [
176 {
177 "name": "stdout",
178 "output_type": "stream",
179 "text": [
180 "Train on 500 samples\n",
181 "Epoch 1/100\n",
182 "500/500 [==============================] - 0s 399us/sample - loss: 247.2794 - accuracy: 0.0040\n",
183 "Epoch 2/100\n",
184 "500/500 [==============================] - 0s 121us/sample - loss: 4.2495 - accuracy: 0.0060\n",
185 "Epoch 3/100\n",
186 "500/500 [==============================] - 0s 131us/sample - loss: 1.8787 - accuracy: 0.0040\n",
187 "Epoch 4/100\n",
188 "500/500 [==============================] - 0s 121us/sample - loss: 0.4284 - accuracy: 0.0060\n",
189 "Epoch 5/100\n",
190 "500/500 [==============================] - 0s 107us/sample - loss: 4.7904 - accuracy: 0.0080\n",
191 "Epoch 6/100\n",
192 "500/500 [==============================] - 0s 113us/sample - loss: 0.0819 - accuracy: 0.0040\n",
193 "Epoch 7/100\n",
194 "500/500 [==============================] - 0s 108us/sample - loss: 1.6904 - accuracy: 0.0040\n",
195 "Epoch 8/100\n",
196 "500/500 [==============================] - 0s 116us/sample - loss: 0.1761 - accuracy: 0.0040\n",
197 "Epoch 9/100\n",
198 "500/500 [==============================] - 0s 142us/sample - loss: 0.1135 - accuracy: 0.0040\n",
199 "Epoch 10/100\n",
200 "500/500 [==============================] - 0s 124us/sample - loss: 0.4387 - accuracy: 0.0040\n",
201 "Epoch 11/100\n",
202 "500/500 [==============================] - 0s 112us/sample - loss: 0.0815 - accuracy: 0.0040\n",
203 "Epoch 12/100\n",
204 "500/500 [==============================] - 0s 117us/sample - loss: 0.1725 - accuracy: 0.0040\n",
205 "Epoch 13/100\n",
206 "500/500 [==============================] - 0s 119us/sample - loss: 0.1487 - accuracy: 0.0040\n",
207 "Epoch 14/100\n",
208 "500/500 [==============================] - 0s 111us/sample - loss: 0.0720 - accuracy: 0.0040\n",
209 "Epoch 15/100\n",
210 "500/500 [==============================] - 0s 111us/sample - loss: 0.3110 - accuracy: 0.0040\n",
211 "Epoch 16/100\n",
212 "500/500 [==============================] - 0s 128us/sample - loss: 0.0947 - accuracy: 0.0040\n",
213 "Epoch 17/100\n",
214 "500/500 [==============================] - 0s 133us/sample - loss: 0.0739 - accuracy: 0.0040\n",
215 "Epoch 18/100\n",
216 "500/500 [==============================] - 0s 131us/sample - loss: 0.1353 - accuracy: 0.0060\n",
217 "Epoch 19/100\n",
218 "500/500 [==============================] - 0s 135us/sample - loss: 0.0837 - accuracy: 0.0040\n",
219 "Epoch 20/100\n",
220 "500/500 [==============================] - 0s 130us/sample - loss: 0.0754 - accuracy: 0.0040\n",
221 "Epoch 21/100\n",
222 "500/500 [==============================] - 0s 118us/sample - loss: 0.0840 - accuracy: 0.0040\n",
223 "Epoch 22/100\n",
224 "500/500 [==============================] - 0s 115us/sample - loss: 0.1105 - accuracy: 0.0040\n",
225 "Epoch 23/100\n",
226 "500/500 [==============================] - 0s 116us/sample - loss: 0.0651 - accuracy: 0.0040\n",
227 "Epoch 24/100\n",
228 "500/500 [==============================] - 0s 109us/sample - loss: 0.0615 - accuracy: 0.0040\n",
229 "Epoch 25/100\n",
230 "500/500 [==============================] - 0s 118us/sample - loss: 0.0656 - accuracy: 0.0040\n",
231 "Epoch 26/100\n",
232 "500/500 [==============================] - 0s 113us/sample - loss: 0.0695 - accuracy: 0.0040\n",
233 "Epoch 27/100\n",
234 "500/500 [==============================] - 0s 116us/sample - loss: 0.0585 - accuracy: 0.0040\n",
235 "Epoch 28/100\n",
236 "500/500 [==============================] - 0s 118us/sample - loss: 0.1300 - accuracy: 0.0040\n",
237 "Epoch 29/100\n",
238 "500/500 [==============================] - 0s 112us/sample - loss: 0.0567 - accuracy: 0.0040\n",
239 "Epoch 30/100\n",
240 "500/500 [==============================] - 0s 137us/sample - loss: 0.0647 - accuracy: 0.0040\n",
241 "Epoch 31/100\n",
242 "500/500 [==============================] - 0s 130us/sample - loss: 0.0559 - accuracy: 0.0040\n",
243 "Epoch 32/100\n",
244 "500/500 [==============================] - 0s 130us/sample - loss: 0.0576 - accuracy: 0.0040\n",
245 "Epoch 33/100\n",
246 "500/500 [==============================] - 0s 128us/sample - loss: 0.0578 - accuracy: 0.0040\n",
247 "Epoch 34/100\n",
248 "500/500 [==============================] - 0s 130us/sample - loss: 0.0512 - accuracy: 0.0040\n",
249 "Epoch 35/100\n",
250 "500/500 [==============================] - 0s 114us/sample - loss: 0.0601 - accuracy: 0.0040\n",
251 "Epoch 36/100\n",
252 "500/500 [==============================] - 0s 111us/sample - loss: 0.0531 - accuracy: 0.0040\n",
253 "Epoch 37/100\n",
254 "500/500 [==============================] - 0s 130us/sample - loss: 0.0532 - accuracy: 0.0040\n",
255 "Epoch 38/100\n",
256 "500/500 [==============================] - 0s 131us/sample - loss: 0.0480 - accuracy: 0.0040\n",
257 "Epoch 39/100\n",
258 "500/500 [==============================] - 0s 136us/sample - loss: 0.0503 - accuracy: 0.0040\n",
259 "Epoch 40/100\n",
260 "500/500 [==============================] - 0s 134us/sample - loss: 0.0468 - accuracy: 0.0040\n",
261 "Epoch 41/100\n",
262 "500/500 [==============================] - 0s 115us/sample - loss: 0.0509 - accuracy: 0.0040\n",
263 "Epoch 42/100\n",
264 "500/500 [==============================] - 0s 109us/sample - loss: 0.0453 - accuracy: 0.0040\n",
265 "Epoch 43/100\n",
266 "500/500 [==============================] - 0s 111us/sample - loss: 0.0484 - accuracy: 0.0040\n",
267 "Epoch 44/100\n",
268 "500/500 [==============================] - 0s 104us/sample - loss: 0.0458 - accuracy: 0.0040\n",
269 "Epoch 45/100\n",
270 "500/500 [==============================] - 0s 110us/sample - loss: 0.0481 - accuracy: 0.0040\n",
271 "Epoch 46/100\n",
272 "500/500 [==============================] - 0s 114us/sample - loss: 0.0468 - accuracy: 0.0060\n",
273 "Epoch 47/100\n",
274 "500/500 [==============================] - 0s 124us/sample - loss: 0.0473 - accuracy: 0.0060\n",
275 "Epoch 48/100\n",
276 "500/500 [==============================] - 0s 137us/sample - loss: 0.0455 - accuracy: 0.0040\n",
277 "Epoch 49/100\n",
278 "500/500 [==============================] - 0s 125us/sample - loss: 0.0431 - accuracy: 0.0060\n",
279 "Epoch 50/100\n",
280 "500/500 [==============================] - 0s 132us/sample - loss: 0.0432 - accuracy: 0.0060\n",
281 "Epoch 51/100\n",
282 "500/500 [==============================] - 0s 116us/sample - loss: 0.0484 - accuracy: 0.0060\n",
283 "Epoch 52/100\n",
284 "500/500 [==============================] - 0s 112us/sample - loss: 0.0482 - accuracy: 0.0040\n",
285 "Epoch 53/100\n",
286 "500/500 [==============================] - 0s 117us/sample - loss: 0.0444 - accuracy: 0.0060\n",
287 "Epoch 54/100\n",
288 "500/500 [==============================] - 0s 109us/sample - loss: 0.0469 - accuracy: 0.0060\n",
289 "Epoch 55/100\n",
290 "500/500 [==============================] - 0s 106us/sample - loss: 0.0427 - accuracy: 0.0040\n",
291 "Epoch 56/100\n",
292 "500/500 [==============================] - 0s 110us/sample - loss: 0.0433 - accuracy: 0.0040\n",
293 "Epoch 57/100\n",
294 "500/500 [==============================] - 0s 102us/sample - loss: 0.0437 - accuracy: 0.0060\n",
295 "Epoch 58/100\n",
296 "500/500 [==============================] - 0s 117us/sample - loss: 0.0425 - accuracy: 0.0040\n",
297 "Epoch 59/100\n",
298 "500/500 [==============================] - 0s 105us/sample - loss: 0.0418 - accuracy: 0.0040\n",
299 "Epoch 60/100\n",
300 "500/500 [==============================] - 0s 109us/sample - loss: 0.0397 - accuracy: 0.0040\n",
301 "Epoch 61/100\n",
302 "500/500 [==============================] - 0s 119us/sample - loss: 0.0507 - accuracy: 0.0040\n",
303 "Epoch 62/100\n",
304 "500/500 [==============================] - 0s 112us/sample - loss: 0.0402 - accuracy: 0.0060\n",
305 "Epoch 63/100\n",
306 "500/500 [==============================] - 0s 133us/sample - loss: 0.0397 - accuracy: 0.0040\n",
307 "Epoch 64/100\n",
308 "500/500 [==============================] - 0s 132us/sample - loss: 0.0427 - accuracy: 0.0060\n",
309 "Epoch 65/100\n",
310 "500/500 [==============================] - 0s 138us/sample - loss: 0.0398 - accuracy: 0.0040\n",
311 "Epoch 66/100\n",
312 "500/500 [==============================] - 0s 145us/sample - loss: 0.0375 - accuracy: 0.0060\n",
313 "Epoch 67/100\n",
314 "500/500 [==============================] - 0s 138us/sample - loss: 0.0402 - accuracy: 0.0060\n",
315 "Epoch 68/100\n",
316 "500/500 [==============================] - 0s 132us/sample - loss: 0.0388 - accuracy: 0.0080\n",
317 "Epoch 69/100\n",
318 "500/500 [==============================] - 0s 115us/sample - loss: 0.0375 - accuracy: 0.0080\n",
319 "Epoch 70/100\n",
320 "500/500 [==============================] - 0s 113us/sample - loss: 0.0384 - accuracy: 0.0040\n",
321 "Epoch 71/100\n",
322 "500/500 [==============================] - 0s 109us/sample - loss: 0.0360 - accuracy: 0.0080\n",
323 "Epoch 72/100\n",
324 "500/500 [==============================] - 0s 111us/sample - loss: 0.0350 - accuracy: 0.0080\n",
325 "Epoch 73/100\n",
326 "500/500 [==============================] - 0s 118us/sample - loss: 0.0370 - accuracy: 0.0060\n",
327 "Epoch 74/100\n",
328 "500/500 [==============================] - 0s 95us/sample - loss: 0.0354 - accuracy: 0.0080\n",
329 "Epoch 75/100\n",
330 "500/500 [==============================] - 0s 102us/sample - loss: 0.0376 - accuracy: 0.0060\n",
331 "Epoch 76/100\n",
332 "500/500 [==============================] - 0s 106us/sample - loss: 0.0371 - accuracy: 0.0080\n",
333 "Epoch 77/100\n",
334 "500/500 [==============================] - 0s 100us/sample - loss: 0.0369 - accuracy: 0.0060\n",
335 "Epoch 78/100\n"
336 ]
337 },
338 {
339 "name": "stdout",
340 "output_type": "stream",
341 "text": [
342 "500/500 [==============================] - 0s 98us/sample - loss: 0.0315 - accuracy: 0.0060\n",
343 "Epoch 79/100\n",
344 "500/500 [==============================] - 0s 97us/sample - loss: 0.0355 - accuracy: 0.0060\n",
345 "Epoch 80/100\n",
346 "500/500 [==============================] - 0s 100us/sample - loss: 0.0278 - accuracy: 0.0080\n",
347 "Epoch 81/100\n",
348 "500/500 [==============================] - 0s 99us/sample - loss: 0.0320 - accuracy: 0.0080\n",
349 "Epoch 82/100\n",
350 "500/500 [==============================] - 0s 99us/sample - loss: 0.0321 - accuracy: 0.0080\n",
351 "Epoch 83/100\n",
352 "500/500 [==============================] - 0s 94us/sample - loss: 0.0332 - accuracy: 0.0060\n",
353 "Epoch 84/100\n",
354 "500/500 [==============================] - 0s 106us/sample - loss: 0.0317 - accuracy: 0.0060\n",
355 "Epoch 85/100\n",
356 "500/500 [==============================] - 0s 103us/sample - loss: 0.0293 - accuracy: 0.0080\n",
357 "Epoch 86/100\n",
358 "500/500 [==============================] - 0s 107us/sample - loss: 0.0304 - accuracy: 0.0060\n",
359 "Epoch 87/100\n",
360 "500/500 [==============================] - 0s 101us/sample - loss: 0.0327 - accuracy: 0.0040\n",
361 "Epoch 88/100\n",
362 "500/500 [==============================] - 0s 100us/sample - loss: 0.0290 - accuracy: 0.0080\n",
363 "Epoch 89/100\n",
364 "500/500 [==============================] - 0s 123us/sample - loss: 0.0293 - accuracy: 0.0060\n",
365 "Epoch 90/100\n",
366 "500/500 [==============================] - 0s 104us/sample - loss: 0.0246 - accuracy: 0.0060\n",
367 "Epoch 91/100\n",
368 "500/500 [==============================] - 0s 124us/sample - loss: 0.0303 - accuracy: 0.0060\n",
369 "Epoch 92/100\n",
370 "500/500 [==============================] - 0s 129us/sample - loss: 0.0376 - accuracy: 0.0080\n",
371 "Epoch 93/100\n",
372 "500/500 [==============================] - 0s 122us/sample - loss: 0.0264 - accuracy: 0.0080\n",
373 "Epoch 94/100\n",
374 "500/500 [==============================] - 0s 102us/sample - loss: 0.0265 - accuracy: 0.0080\n",
375 "Epoch 95/100\n",
376 "500/500 [==============================] - 0s 108us/sample - loss: 0.0291 - accuracy: 0.0080\n",
377 "Epoch 96/100\n",
378 "500/500 [==============================] - 0s 101us/sample - loss: 0.0314 - accuracy: 0.0080\n",
379 "Epoch 97/100\n",
380 "500/500 [==============================] - 0s 95us/sample - loss: 0.0257 - accuracy: 0.0060\n",
381 "Epoch 98/100\n",
382 "500/500 [==============================] - 0s 100us/sample - loss: 0.0248 - accuracy: 0.0080\n",
383 "Epoch 99/100\n",
384 "500/500 [==============================] - 0s 94us/sample - loss: 0.0250 - accuracy: 0.0040\n",
385 "Epoch 100/100\n",
386 "500/500 [==============================] - 0s 106us/sample - loss: 0.0312 - accuracy: 0.0060\n"
387 ]
388 },
389 {
390 "data": {
391 "text/plain": [
392 "<tensorflow.python.keras.callbacks.History at 0x7f55a3853f60>"
393 ]
394 },
395 "execution_count": 8,
396 "metadata": {},
397 "output_type": "execute_result"
398 }
399 ],
400 "source": [
401 "#model.fit(data_input_train, data_labels_train, validation_data=(data_input_test, data_labels_test), epochs=100)\n",
402 "model.fit(data_input_train, data_labels_train, epochs=100)"
403 ]
404 },
405 {
406 "cell_type": "code",
407 "execution_count": 9,
408 "metadata": {},
409 "outputs": [
410 {
411 "name": "stdout",
412 "output_type": "stream",
413 "text": [
414 "100/100 - 0s - loss: 0.0470 - accuracy: 0.0100\n",
415 "\n",
416 "Test accuracy: 0.01\n"
417 ]
418 }
419 ],
420 "source": [
421 "test_loss, test_acc = model.evaluate(data_input_test, data_labels_test, verbose=2)\n",
422 "\n",
423 "print('\\nTest accuracy:', test_acc)"
424 ]
425 },
426 {
427 "cell_type": "code",
428 "execution_count": 10,
429 "metadata": {},
430 "outputs": [
431 {
432 "name": "stdout",
433 "output_type": "stream",
434 "text": [
435 "[[0.3141548]]\n"
436 ]
437 }
438 ],
439 "source": [
440 "input = np.array([0.46,2,136])\n",
441 "input.shape = (1,3)\n",
442 "\n",
443 "prediction = model.predict(input)\n",
444 "print(prediction)"
445 ]
446 },
447 {
448 "cell_type": "code",
449 "execution_count": 11,
450 "metadata": {},
451 "outputs": [],
452 "source": [
453 "predictions = model.predict(data_input_test)"
454 ]
455 },
456 {
457 "cell_type": "code",
458 "execution_count": 12,
459 "metadata": {},
460 "outputs": [],
461 "source": [
462 "%matplotlib qt \n",
463 "plt.plot(predictions)\n",
464 "plt.plot(data_labels_test, 'r')\n",
465 "plt.show()"
466 ]
467 },
468 {
469 "cell_type": "code",
470 "execution_count": 204,
471 "metadata": {},
472 "outputs": [],
473 "source": [
474 "%matplotlib qt\n",
475 "a = data_labels_test - predictions\n",
476 "plt.plot(a[0])\n",
477 "plt.show()"
478 ]
479 },
480 {
481 "cell_type": "code",
482 "execution_count": 207,
483 "metadata": {},
484 "outputs": [],
485 "source": [
486 "%matplotlib qt\n",
487 "a = data_labels_test - predictions\n",
488 "plt.plot(predictions)\n",
489 "plt.plot(data_labels_test, 'r')\n",
490 "plt.plot(a[0], 'g')\n",
491 "plt.show()"
492 ]
493 },
494 {
495 "cell_type": "code",
496 "execution_count": 180,
497 "metadata": {},
498 "outputs": [
499 {
500 "data": {
501 "text/plain": [
502 "-0.08489150602276586"
503 ]
504 },
505 "execution_count": 180,
506 "metadata": {},
507 "output_type": "execute_result"
508 }
509 ],
510 "source": [
511 "np.average(a[0])"
512 ]
513 },
514 {
515 "cell_type": "code",
516 "execution_count": 182,
517 "metadata": {},
518 "outputs": [
519 {
520 "name": "stdout",
521 "output_type": "stream",
522 "text": [
523 "Model: \"sequential_13\"\n",
524 "_________________________________________________________________\n",
525 "Layer (type) Output Shape Param # \n",
526 "=================================================================\n",
527 "dense_38 (Dense) (None, 128) 512 \n",
528 "_________________________________________________________________\n",
529 "dense_39 (Dense) (None, 512) 66048 \n",
530 "_________________________________________________________________\n",
531 "dense_40 (Dense) (None, 512) 262656 \n",
532 "_________________________________________________________________\n",
533 "dense_41 (Dense) (None, 512) 262656 \n",
534 "_________________________________________________________________\n",
535 "dense_42 (Dense) (None, 128) 65664 \n",
536 "_________________________________________________________________\n",
537 "dense_43 (Dense) (None, 1) 129 \n",
538 "=================================================================\n",
539 "Total params: 657,665\n",
540 "Trainable params: 657,665\n",
541 "Non-trainable params: 0\n",
542 "_________________________________________________________________\n"
543 ]
544 }
545 ],
546 "source": [
547 "model.summary()"
548 ]
549 },
550 {
551 "cell_type": "code",
552 "execution_count": 183,
553 "metadata": {},
554 "outputs": [],
555 "source": [
556 "model.save('my_model.h5')"
557 ]
558 },
559 {
560 "cell_type": "code",
561 "execution_count": null,
562 "metadata": {},
563 "outputs": [],
564 "source": []
565 }
566 ],
567 "metadata": {
568 "kernelspec": {
569 "display_name": "Python 3",
570 "language": "python",
571 "name": "python3"
572 },
573 "language_info": {
574 "codemirror_mode": {
575 "name": "ipython",
576 "version": 3
577 },
578 "file_extension": ".py",
579 "mimetype": "text/x-python",
580 "name": "python",
581 "nbconvert_exporter": "python",
582 "pygments_lexer": "ipython3",
583 "version": "3.7.3"
584 }
585 },
586 "nbformat": 4,
587 "nbformat_minor": 2
588}