Clase Inteligencia artificial semana 11

Esta é uma pré-visualização de arquivo. Entre para ver o arquivo original

{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"provenance":[],"collapsed_sections":[],"authorship_tag":"ABX9TyN3HqSt9RuS6xHsPK/eToKl"},"kernelspec":{"name":"python3","display_name":"Python 3"},"language_info":{"name":"python"}},"cells":[{"cell_type":"markdown","source":["#Regresión lineal\n","Y = etiquetas\n","\n","X = caracteristicas\n","\n","Se pueden trazar varias lineas y calcular el error mediante el RSE y que quede más aceptable \n","\n","Su principal objetivo es minimizar el error\n","\n","Para resolver esa sumatoria necesitamos acomodar la ecuación en forma que se multiplica la transpuesta por la normal para obtener el siguiente resultado:\n","\n","d/d0 = Xt(x0-y) + x(x0-y)T\n","\n","2Qt +dq/d0\n","\n","2(x0-Y)^T*x = 0\n","\n","x^T(x0-y) = 0\n","\n","x^Tx0-x^Ty = 0\n","\n","x^Tx0 = x^Ty\n","\n","#Ecuación normal\n","0=(x^Tx)^-1x^Ty\n"],"metadata":{"id":"N32ATaS3mWu3"}},{"cell_type":"code","execution_count":1,"metadata":{"id":"Kam7hftojSDL","executionInfo":{"status":"ok","timestamp":1664496737713,"user_tz":300,"elapsed":17,"user":{"displayName":"Santiago Piedrahíta Perez","userId":"09826084650905491344"}}},"outputs":[],"source":["#Codigo para hacer la regresión lineal \n","import numpy as np \n","X = 2 * np.random.rand(100,1)\n","y = 4 + 3 * X + np.random.randn(100,1)\n"]},{"cell_type":"code","source":["#Encontrando los puntos\n","import matplotlib.pyplot as plt\n","\n","plt.xlabel(\"Caracteristicas\")\n","plt.ylabel(\"Resultado\")\n","plt.scatter(X,y)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":296},"id":"aJ7oaM8BvLap","executionInfo":{"status":"ok","timestamp":1664496956744,"user_tz":300,"elapsed":623,"user":{"displayName":"Santiago Piedrahíta Perez","userId":"09826084650905491344"}},"outputId":"669f50ac-3566-4e44-b9cd-dc4c2e7dfc2d"},"execution_count":4,"outputs":[{"output_type":"execute_result","data":{"text/plain":["<matplotlib.collections.PathCollection at 0x7fde9df06310>"]},"metadata":{},"execution_count":4},{"output_type":"display_data","data":{"text/plain":["<Figure size 432x288 with 1 Axes>"],"image/png":"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\n"},"metadata":{"needs_background":"light"}}]},{"cell_type":"code","source":["xT
= np.transpose(X)\n","Xin= np.linalg.inv(xT*X)\n","print(Xin)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"UF9yuBqOwAfj","executionInfo":{"status":"ok","timestamp":1664497246047,"user_tz":300,"elapsed":248,"user":{"displayName":"Santiago Piedrahíta Perez","userId":"09826084650905491344"}},"outputId":"ae8c82ae-8b78-452c-def3-d42b90f01443"},"execution_count":8,"outputs":[{"output_type":"stream","name":"stdout","text":["[[-8.50335741e+15 3.62383105e+18 -8.04987135e+15 ... 7.67817535e+15\n"," -8.69589426e+16 -3.47811805e+16]\n"," [-5.47852891e+17 -6.71117449e+19 7.72809330e+14 ... -1.51515388e+17\n"," 2.17551429e+18 6.70245818e+17]\n"," [-4.03689495e+15 -1.00950663e+18 2.25903343e+15 ... -2.58478765e+15\n"," 2.65983438e+16 1.04784670e+16]\n"," ...\n"," [ 3.11524349e+15 1.18057406e+17 3.37870713e+14 ... 3.65171762e+14\n"," -5.36820230e+15 -1.37073663e+15]\n"," [-6.05922480e+15 -6.38689185e+17 1.02717548e+15 ... -2.12262222e+15\n"," 1.55567972e+16 8.32783248e+15]\n"," [ 1.23450645e+16 5.99149308e+17 1.54977415e+14 ... 1.24871597e+15\n"," -1.75606980e+16 -6.94005729e+15]]\n"]}]},{"cell_type":"code","source":["x0=Xin*xT*y\n","print(x0)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"2ciN9TcLw006","executionInfo":{"status":"ok","timestamp":1664497281507,"user_tz":300,"elapsed":25,"user":{"displayName":"Santiago Piedrahíta Perez","userId":"09826084650905491344"}},"outputId":"5b821794-8a5e-4796-a79c-fac337444142"},"execution_count":9,"outputs":[{"output_type":"stream","name":"stdout","text":["[[-1.26722940e+16 1.77343470e+17 -5.12017870e+16 ... 5.59560283e+16\n"," -1.34721318e+17 -1.58534601e+17]\n"," [-6.26771852e+17 -2.52131155e+18 3.77354260e+15 ... -8.47669037e+17\n"," 2.58740692e+18 2.34527936e+18]\n"," [-9.22050402e+15 -7.57179498e+16 2.20222276e+16 ... -2.88706215e+16\n"," 6.31566486e+16 7.32014875e+16]\n"," ...\n"," [ 6.64697891e+15 8.27195184e+15 3.07690599e+15 ... 3.81025061e+15\n"," -1.19074412e+16 -8.94543088e+15]\n"," [-9.26856136e+15 -3.20824320e+16 6.70611942e+15 ... -1.58778619e+16\n"," 2.47384635e+16 3.89620847e+16]\n"," [ 2.44593655e+16 3.89824688e+16 1.31054401e+15 ... 1.20987231e+16\n"," -3.61701960e+16 -4.20561796e+16]]\n"]}]},{"cell_type":"code","source":["#Ecuacion normal\n","Xb= np.c_[np.ones((100,1),),X]\n","theta_best = np.linalg.inv(Xb.T.dot(Xb)).dot(Xb.T).dot(y)\n","print(theta_best)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"QGMhxqFuxrL6","executionInfo":{"status":"ok","timestamp":1664497576150,"user_tz":300,"elapsed":256,"user":{"displayName":"Santiago Piedrahíta Perez","userId":"09826084650905491344"}},"outputId":"ef33a8ac-158f-4d29-b6cb-52fe0664a4e2"},"execution_count":11,"outputs":[{"output_type":"stream","name":"stdout","text":["[[4.23929945]\n"," [2.81929823]]\n"]}]},{"cell_type":"code","source":["X_new = np.array([[0],[2]])\n","X_new_b = np.c_[np.ones((2,1)), X_new]\n","y_predict = X_new_b.dot(theta_best)\n","y_predict"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"At0U0almyY-M","executionInfo":{"status":"ok","timestamp":1664497711511,"user_tz":300,"elapsed":19,"user":{"displayName":"Santiago Piedrahíta Perez","userId":"09826084650905491344"}},"outputId":"e6e2c5f8-b5e7-44ea-9c64-9b5eeb9c0ce3"},"execution_count":13,"outputs":[{"output_type":"execute_result","data":{"text/plain":["array([[4.23929945],\n"," [9.87789592]])"]},"metadata":{},"execution_count":13}]},{"cell_type":"code","source":["plt.plot(X_new,y_predict,\"r-\")\n","plt.plot(X,y,\"b.\")\n","plt.axis([0,2,0,15])\n","plt.show"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":282},"id":"I_Yowp4ly5Md","executionInfo":{"status":"ok","timestamp":1664498009635,"user_tz":300,"elapsed":472,"user":{"displayName":"Santiago Piedrahíta Perez","userId":"09826084650905491344"}},"outputId":"67a9cd10-d6db-4120-8f82-9c1abf4a672e"},"execution_count":14,"outputs":[{"output_type":"execute_result","data":{"text/plain":["<function matplotlib.pyplot.show(*args, **kw)>"]},"metadata":{},"execution_count":14},{"output_type":"display_data","data":{"text/plain":["<Figure size 432x288 with 1 Axes>"],"image/png":"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\n"},"metadata":{"needs_background":"light"}}]},{"cell_type":"markdown","source":["#Nota:
\n","cuando se usa descenso del gradiente se deben utilizar caracteristicas en el mismo rango de valores, de lo contrario el algoritmo tratará más en converger."],"metadata":{"id":"pZvbQAhV4uxM"}},{"cell_type":"code","source":["eta = 0.1 #leyendo los datos\n","n_iterations = 10000\n","m = 100\n","theta= np.random.randn(2,1) #Inicialización random \n","for iteration in range(n_iterations):\n"," gradients = 2/m * Xb.T.dot(Xb.dot(theta)-y)\n"," theta = theta - eta * gradients\n"," \n","theta"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"Asak0QuE3K98","executionInfo":{"status":"ok","timestamp":1664500022299,"user_tz":300,"elapsed":258,"user":{"displayName":"Santiago Piedrahíta Perez","userId":"09826084650905491344"}},"outputId":"dbb2a2f9-32d4-4158-fa58-99ea95b23e94"},"execution_count":19,"outputs":[{"output_type":"execute_result","data":{"text/plain":["array([[4.23929945],\n"," [2.81929823]])"]},"metadata":{},"execution_count":19}]}]}