{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "##### 교재 페이지 (149-151) #####" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "6-3) Loading data from file" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "(25, 3) [[ 73. 80. 75.]\n", " [ 93. 88. 93.]\n", " [ 89. 91. 90.]\n", " [ 96. 98. 100.]\n", " [ 73. 66. 70.]\n", " [ 53. 46. 55.]\n", " [ 69. 74. 77.]\n", " [ 47. 56. 60.]\n", " [ 87. 79. 90.]\n", " [ 79. 70. 88.]\n", " [ 69. 70. 73.]\n", " [ 70. 65. 74.]\n", " [ 93. 95. 91.]\n", " [ 79. 80. 73.]\n", " [ 70. 73. 78.]\n", " [ 93. 89. 96.]\n", " [ 78. 75. 68.]\n", " [ 81. 90. 93.]\n", " [ 88. 92. 86.]\n", " [ 78. 83. 77.]\n", " [ 82. 86. 90.]\n", " [ 86. 82. 89.]\n", " [ 78. 83. 85.]\n", " [ 76. 83. 71.]\n", " [ 96. 93. 95.]] 25\n", "(25, 1) [[152.]\n", " [185.]\n", " [180.]\n", " [196.]\n", " [142.]\n", " [101.]\n", " [149.]\n", " [115.]\n", " [175.]\n", " [164.]\n", " [141.]\n", " [141.]\n", " [184.]\n", " [152.]\n", " [148.]\n", " [192.]\n", " [147.]\n", " [183.]\n", " [177.]\n", " [159.]\n", " [177.]\n", " [175.]\n", " [175.]\n", " [149.]\n", " [192.]]\n", "WARNING:tensorflow:From C:\\Users\\jsdata00010\\Anaconda3\\lib\\site-packages\\tensorflow\\python\\framework\\op_def_library.py:263: colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version.\n", "Instructions for updating:\n", "Colocations handled automatically by placer.\n", "0 Cost: 21027.002 \n", "Prediction:\n", " [[22.048063 ]\n", " [21.619787 ]\n", " [24.096693 ]\n", " [22.293005 ]\n", " [18.633902 ]\n", " [ 7.2669735]\n", " [12.33103 ]\n", " [ 3.150511 ]\n", " [14.347944 ]\n", " [ 4.2534237]\n", " [14.485708 ]\n", " [10.678068 ]\n", " [28.80464 ]\n", " [29.298803 ]\n", " [11.237837 ]\n", " [18.646544 ]\n", " [31.189451 ]\n", " [13.344664 ]\n", " [28.841742 ]\n", " [25.66281 ]\n", " [15.084761 ]\n", " [16.798368 ]\n", " [15.924551 ]\n", " [31.36112 ]\n", " [24.986364 ]]\n", "10000 Cost: 6.3075275 \n", "Prediction:\n", " [[152.80807]\n", " [184.83162]\n", " [181.37848]\n", " [198.6599 ]\n", " [140.42346]\n", " [105.59277]\n", " [150.19682]\n", " [113.35465]\n", " [174.4844 ]\n", " [164.33716]\n", " [143.90251]\n", " [142.90082]\n", " [186.20119]\n", " [153.27995]\n", " [151.20258]\n", " [188.54863]\n", " [144.97618]\n", " [180.6047 ]\n", " [177.1576 ]\n", " [158.63654]\n", " [175.818 ]\n", " [174.48239]\n", " [167.21028]\n", " [151.33444]\n", " [190.792 ]]\n", "20000 Cost: 6.178985 \n", "Prediction:\n", " [[152.9591 ]\n", " [184.57266 ]\n", " [181.3407 ]\n", " [198.75731 ]\n", " [139.99829 ]\n", " [105.43419 ]\n", " [150.59377 ]\n", " [114.116684]\n", " [174.30566 ]\n", " [164.4335 ]\n", " [144.01111 ]\n", " [142.86426 ]\n", " [186.01385 ]\n", " [152.89445 ]\n", " [151.55026 ]\n", " [188.45798 ]\n", " [144.30365 ]\n", " [181.27435 ]\n", " [177.02472 ]\n", " [158.58878 ]\n", " [176.17403 ]\n", " [174.40085 ]\n", " [167.5474 ]\n", " [151.1448 ]\n", " [190.52899 ]]\n", "30000 Cost: 6.1748047 \n", "Prediction:\n", " [[152.97697]\n", " [184.55052]\n", " [181.34233]\n", " [198.76901]\n", " [139.9584 ]\n", " [105.40722]\n", " [150.62352]\n", " [114.17121]\n", " [174.28294]\n", " [164.42522]\n", " [144.01646]\n", " [142.85158]\n", " [186.00676]\n", " [152.8703 ]\n", " [151.57408]\n", " [188.44809]\n", " [144.25496]\n", " [181.32999]\n", " [177.02306]\n", " [158.59196]\n", " [176.20236]\n", " [174.3901 ]\n", " [167.57518]\n", " [151.14151]\n", " [190.51021]]\n", "40000 Cost: 6.171448 \n", "Prediction:\n", " [[152.97725]\n", " [184.55067]\n", " [181.34413]\n", " [198.77333]\n", " [139.95264]\n", " [105.39878]\n", " [150.62428]\n", " [114.17013]\n", " [174.28183]\n", " [164.42403]\n", " [144.01466]\n", " [142.8481 ]\n", " [186.00845]\n", " [152.86736]\n", " [151.57442]\n", " [188.44954]\n", " [144.24924]\n", " [181.33589]\n", " [177.0243 ]\n", " [158.59172]\n", " [176.2056 ]\n", " [174.39003]\n", " [167.57755]\n", " [151.14015]\n", " [190.5113 ]]\n", "50000 Cost: 6.1681185 \n", "Prediction:\n", " [[152.97597]\n", " [184.55261]\n", " [181.34586]\n", " [198.77707]\n", " [139.94954]\n", " [105.39211]\n", " [150.62294]\n", " [114.16508]\n", " [174.28273]\n", " [164.42409]\n", " [144.01239]\n", " [142.84563]\n", " [186.01054]\n", " [152.86565]\n", " [151.57318]\n", " [188.45204]\n", " [144.24638]\n", " [181.33815]\n", " [177.02544]\n", " [158.5909 ]\n", " [176.20706]\n", " [174.391 ]\n", " [167.57805]\n", " [151.13837]\n", " [190.51387]]\n", "60000 Cost: 6.164828 \n", "Prediction:\n", " [[152.97461]\n", " [184.55458]\n", " [181.34755]\n", " [198.7808 ]\n", " [139.94647]\n", " [105.3855 ]\n", " [150.62161]\n", " [114.15999]\n", " [174.2837 ]\n", " [164.42426]\n", " [144.01013]\n", " [142.84322]\n", " [186.01262]\n", " [152.8639 ]\n", " [151.57195]\n", " [188.45457]\n", " [144.24347]\n", " [181.34038]\n", " [177.02655]\n", " [158.59001]\n", " [176.20853]\n", " [174.392 ]\n", " [167.57852]\n", " [151.1365 ]\n", " [190.51645]]\n", "70000 Cost: 6.161523 \n", "Prediction:\n", " [[152.97318]\n", " [184.5566 ]\n", " [181.34921]\n", " [198.78452]\n", " [139.94348]\n", " [105.37895]\n", " [150.62022]\n", " [114.15482]\n", " [174.28476]\n", " [164.42453]\n", " [144.00784]\n", " [142.84085]\n", " [186.01465]\n", " [152.86212]\n", " [151.57066]\n", " [188.45715]\n", " [144.24059]\n", " [181.34251]\n", " [177.02756]\n", " [158.58907]\n", " [176.20995]\n", " [174.39304]\n", " [167.57893]\n", " [151.13452]\n", " [190.51906]]\n", "80000 Cost: 6.1582813 \n", "Prediction:\n", " [[152.97179]\n", " [184.55864]\n", " [181.35089]\n", " [198.78825]\n", " [139.94054]\n", " [105.37247]\n", " [150.61885]\n", " [114.14969]\n", " [174.28584]\n", " [164.4248 ]\n", " [144.00562]\n", " [142.83853]\n", " [186.01671]\n", " [152.86038]\n", " [151.56941]\n", " [188.45973]\n", " [144.23775]\n", " [181.34465]\n", " [177.02864]\n", " [158.58815]\n", " [176.21138]\n", " [174.39409]\n", " [167.57936]\n", " [151.13261]\n", " [190.52168]]\n", "90000 Cost: 6.155053 \n", "Prediction:\n", " [[152.97038]\n", " [184.56062]\n", " [181.35254]\n", " [198.79192]\n", " [139.9376 ]\n", " [105.36604]\n", " [150.61751]\n", " [114.14459]\n", " [174.28688]\n", " [164.42506]\n", " [144.00337]\n", " [142.83621]\n", " [186.0187 ]\n", " [152.85864]\n", " [151.56818]\n", " [188.4623 ]\n", " [144.23494]\n", " [181.34676]\n", " [177.02966]\n", " [158.58723]\n", " [176.21278]\n", " [174.39513]\n", " [167.57979]\n", " [151.13069]\n", " [190.52426]]\n", "100000 Cost: 6.1518464 \n", "Prediction:\n", " [[152.96898 ]\n", " [184.56264 ]\n", " [181.35419 ]\n", " [198.79558 ]\n", " [139.93466 ]\n", " [105.35962 ]\n", " [150.61613 ]\n", " [114.139496]\n", " [174.28793 ]\n", " [164.42534 ]\n", " [144.00114 ]\n", " [142.83391 ]\n", " [186.02074 ]\n", " [152.85692 ]\n", " [151.56693 ]\n", " [188.46484 ]\n", " [144.23213 ]\n", " [181.34886 ]\n", " [177.03069 ]\n", " [158.58632 ]\n", " [176.21419 ]\n", " [174.39616 ]\n", " [167.58022 ]\n", " [151.12877 ]\n", " [190.52684 ]]\n", "110000 Cost: 6.14867 \n", "Prediction:\n", " [[152.9676 ]\n", " [184.56462]\n", " [181.35583]\n", " [198.79924]\n", " [139.93175]\n", " [105.35318]\n", " [150.61476]\n", " [114.1344 ]\n", " [174.28897]\n", " [164.42558]\n", " [143.99892]\n", " [142.83159]\n", " [186.02275]\n", " [152.8552 ]\n", " [151.56567]\n", " [188.46739]\n", " [144.22932]\n", " [181.35094]\n", " [177.03172]\n", " [158.5854 ]\n", " [176.21556]\n", " [174.39719]\n", " [167.58061]\n", " [151.12688]\n", " [190.52942]]\n", "120000 Cost: 6.145499 \n", "Prediction:\n", " [[152.9662 ]\n", " [184.56662]\n", " [181.35748]\n", " [198.8029 ]\n", " [139.92882]\n", " [105.34676]\n", " [150.61342]\n", " [114.12932]\n", " [174.29002]\n", " [164.42586]\n", " [143.99669]\n", " [142.82927]\n", " [186.02477]\n", " [152.85347]\n", " [151.56444]\n", " [188.46992]\n", " [144.2265 ]\n", " [181.35304]\n", " [177.03276]\n", " [158.58449]\n", " [176.21696]\n", " [174.39822]\n", " [167.58104]\n", " [151.12495]\n", " [190.532 ]]\n", "130000 Cost: 6.1423726 \n", "Prediction:\n", " [[152.96483]\n", " [184.56859]\n", " [181.35912]\n", " [198.8065 ]\n", " [139.92592]\n", " [105.34042]\n", " [150.61208]\n", " [114.1243 ]\n", " [174.29106]\n", " [164.42613]\n", " [143.99449]\n", " [142.82698]\n", " [186.02675]\n", " [152.85176]\n", " [151.5632 ]\n", " [188.47244]\n", " [144.22372]\n", " [181.35512]\n", " [177.03378]\n", " [158.5836 ]\n", " [176.21835]\n", " [174.39925]\n", " [167.58145]\n", " [151.12308]\n", " [190.53455]]\n", "140000 Cost: 6.139267 \n", "Prediction:\n", " [[152.96346]\n", " [184.57054]\n", " [181.36073]\n", " [198.81012]\n", " [139.92305]\n", " [105.3341 ]\n", " [150.61072]\n", " [114.11928]\n", " [174.29208]\n", " [164.42638]\n", " [143.99231]\n", " [142.82472]\n", " [186.02873]\n", " [152.85007]\n", " [151.56197]\n", " [188.47495]\n", " [144.22098]\n", " [181.3572 ]\n", " [177.0348 ]\n", " [158.5827 ]\n", " [176.21974]\n", " [174.40025]\n", " [167.58186]\n", " [151.1212 ]\n", " [190.5371 ]]\n", "150000 Cost: 6.136192 \n", "Prediction:\n", " [[152.96208]\n", " [184.57251]\n", " [181.36237]\n", " [198.81372]\n", " [139.92015]\n", " [105.3278 ]\n", " [150.60938]\n", " [114.11429]\n", " [174.29312]\n", " [164.42664]\n", " [143.99011]\n", " [142.82243]\n", " [186.03072]\n", " [152.84836]\n", " [151.56075]\n", " [188.47745]\n", " [144.2182 ]\n", " [181.35925]\n", " [177.03583]\n", " [158.5818 ]\n", " [176.2211 ]\n", " [174.40128]\n", " [167.58228]\n", " [151.11932]\n", " [190.53961]]\n", "160000 Cost: 6.133125 \n", "Prediction:\n", " [[152.96072 ]\n", " [184.57446 ]\n", " [181.36397 ]\n", " [198.81729 ]\n", " [139.9173 ]\n", " [105.321495]\n", " [150.60803 ]\n", " [114.10928 ]\n", " [174.29413 ]\n", " [164.4269 ]\n", " [143.98793 ]\n", " [142.82018 ]\n", " [186.03268 ]\n", " [152.84668 ]\n", " [151.55951 ]\n", " [188.47993 ]\n", " [144.21547 ]\n", " [181.3613 ]\n", " [177.03683 ]\n", " [158.5809 ]\n", " [176.22247 ]\n", " [174.40228 ]\n", " [167.58267 ]\n", " [151.11746 ]\n", " [190.54214 ]]\n", "170000 Cost: 6.1300926 \n", "Prediction:\n", " [[152.95935]\n", " [184.57642]\n", " [181.36559]\n", " [198.82088]\n", " [139.91444]\n", " [105.31525]\n", " [150.60672]\n", " [114.10434]\n", " [174.29517]\n", " [164.42717]\n", " [143.98576]\n", " [142.81792]\n", " [186.03465]\n", " [152.84499]\n", " [151.5583 ]\n", " [188.48244]\n", " [144.21272]\n", " [181.36334]\n", " [177.03783]\n", " [158.58002]\n", " [176.22383]\n", " [174.40327]\n", " [167.58308]\n", " [151.11559]\n", " [190.54466]]\n", "180000 Cost: 6.127075 \n", "Prediction:\n", " [[152.95801]\n", " [184.57835]\n", " [181.36719]\n", " [198.82442]\n", " [139.91159]\n", " [105.309 ]\n", " [150.6054 ]\n", " [114.09938]\n", " [174.29617]\n", " [164.4274 ]\n", " [143.9836 ]\n", " [142.81567]\n", " [186.03662]\n", " [152.84332]\n", " [151.5571 ]\n", " [188.4849 ]\n", " [144.21 ]\n", " [181.36539]\n", " [177.03885]\n", " [158.57915]\n", " [176.22519]\n", " [174.40428]\n", " [167.5835 ]\n", " [151.11374]\n", " [190.54718]]\n", "190000 Cost: 6.1240983 \n", "Prediction:\n", " [[152.95665]\n", " [184.58028]\n", " [181.36877]\n", " [198.82796]\n", " [139.90877]\n", " [105.30279]\n", " [150.60406]\n", " [114.09445]\n", " [174.29718]\n", " [164.42766]\n", " [143.98143]\n", " [142.81343]\n", " [186.03856]\n", " [152.84164]\n", " [151.5559 ]\n", " [188.48735]\n", " [144.20729]\n", " [181.3674 ]\n", " [177.03986]\n", " [158.57826]\n", " [176.22653]\n", " [174.40529]\n", " [167.58388]\n", " [151.11191]\n", " [190.54967]]\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "200000 Cost: 6.121114 \n", "Prediction:\n", " [[152.9553 ]\n", " [184.58221 ]\n", " [181.37038 ]\n", " [198.8315 ]\n", " [139.90593 ]\n", " [105.296585]\n", " [150.60275 ]\n", " [114.089554]\n", " [174.2982 ]\n", " [164.4279 ]\n", " [143.9793 ]\n", " [142.81119 ]\n", " [186.04051 ]\n", " [152.83998 ]\n", " [151.55469 ]\n", " [188.48982 ]\n", " [144.20457 ]\n", " [181.36943 ]\n", " [177.04085 ]\n", " [158.57738 ]\n", " [176.22789 ]\n", " [174.40627 ]\n", " [167.5843 ]\n", " [151.11006 ]\n", " [190.55215 ]]\n", "Your score will be [[186.54152]]\n", "sales amount will be [[31.713732]]\n" ] } ], "source": [ "import tensorflow as tf\n", "import numpy as np\n", "\n", "tf.set_random_seed(777)\n", "\n", "# for reproducibility\n", "xy = np.loadtxt('data-01-test-score.csv', delimiter=',', dtype=np.float32)\n", "x_data = xy[:, 0:-1]\n", "y_data = xy[:, [-1]]\n", "\n", "# Make sure the shape and data are OK\n", "print(x_data.shape, x_data, len(x_data))\n", "print(y_data.shape, y_data)\n", "\n", "# placeholders for a tensor that will be always fed.\n", "X = tf.placeholder(tf.float32, shape=[None, 3])\n", "Y = tf.placeholder(tf.float32, shape=[None, 1])\n", "W = tf.Variable(tf.random_normal([3, 1]), name='weight')\n", "b = tf.Variable(tf.random_normal([1]), name='bias')\n", "\n", "# Hypothesis\n", "hypothesis = tf.matmul(X, W) + b\n", "\n", "# cost/loss function\n", "cost = tf.reduce_mean(tf.square(hypothesis - Y))\n", "\n", "# Minimize. Need a very small learning rate for this data set\n", "optimizer = tf.train.GradientDescentOptimizer(learning_rate=1e-5)\n", "train = optimizer.minimize(cost)\n", "\n", "# Launch the graph in a session.\n", "sess = tf.Session()\n", "\n", "# Initializes global variables in the graph.\n", "sess.run(tf.global_variables_initializer())\n", "# Set up feed_dict variables inside the loop.\n", "for step in range(200001):\n", " cost_val, hy_val, _ = sess.run([cost, hypothesis, train],\n", " feed_dict={X: x_data, Y: y_data})\n", " if step % 10000 == 0:\n", " print(step, \"Cost: \", cost_val, \"\\nPrediction:\\n\", hy_val)\n", "# Ask my score\n", "print(\"Your score will be \", sess.run(hypothesis,\n", " feed_dict={X: [[100, 70, 101]]}))\n", "# Ask my score\n", "print(\"sales amount will be \", sess.run(hypothesis, \n", " feed_dict={X: [[27,18.1,11,]]}))" ] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.7.3" } }, "nbformat": 4, "nbformat_minor": 2 }