{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"#### This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load in \nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport cv2\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nfrom sklearn.metrics import confusion_matrix\nimport itertools\n# Input data files are available in the \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory\nimport random\nimport os,shutil\n\nsrc_path=\"../input\"\n\nprint(os.listdir(src_path))\n\n#constant value\nVALID_SPIT=0.2\nIMAGE_SIZE=80\nBATCH_SIZE=20","execution_count":1,"outputs":[{"output_type":"stream","text":"['test1', 'sampleSubmission.csv', 'train']\n","name":"stdout"}]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"label=[]\ndata=[]\ncounter=0\npath=\"../input/train/train\"\nfor file in os.listdir(path):\n    image_data=cv2.imread(os.path.join(path,file), cv2.IMREAD_COLOR)\n    image_data=cv2.resize(image_data,(IMAGE_SIZE,IMAGE_SIZE))\n    if file.startswith(\"cat\"):\n        label.append(0)\n    elif file.startswith(\"dog\"):\n        label.append(1)\n    try:\n        data.append(image_data/255)\n    except:\n        label=label[:len(label)-1]\n    counter+=1\n    if counter%1000==0:\n        print (counter,\" image data retreived\")\n\ndata=np.array(data)\ndata=data.reshape((data.shape)[0],(data.shape)[1],(data.shape)[2],3)\nlabel=np.array(label)\nprint (data.shape)\nprint (label.shape)\n","execution_count":3,"outputs":[{"output_type":"stream","text":"1000  image data retreived\n2000  image data retreived\n3000  image data retreived\n4000  image data retreived\n5000  image data retreived\n6000  image data retreived\n7000  image data retreived\n8000  image data retreived\n9000  image data retreived\n10000  image data retreived\n11000  image data retreived\n12000  image data retreived\n13000  image data retreived\n14000  image data retreived\n15000  image data retreived\n16000  image data retreived\n17000  image data retreived\n18000  image data retreived\n19000  image data retreived\n20000  image data retreived\n21000  image data retreived\n22000  image data retreived\n23000  image data retreived\n24000  image data retreived\n25000  image data retreived\n(25000, 80, 80, 3)\n(25000,)\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import train_test_split\ntrain_data, valid_data, train_label, valid_label = train_test_split(\n    data, label, test_size=0.2, random_state=42)\nprint(train_data.shape)\nprint(train_label.shape)\nprint(valid_data.shape)\nprint(valid_label.shape)\n","execution_count":4,"outputs":[{"output_type":"stream","text":"(20000, 80, 80, 3)\n(20000,)\n(5000, 80, 80, 3)\n(5000,)\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras import applications\nvgg_model = applications.VGG16(weights='imagenet',\n                               include_top=False,\n                               pooling='avg',\n                               input_shape=(80, 80, 3))\n\nvgg_model.summary()","execution_count":6,"outputs":[{"output_type":"stream","text":"Using TensorFlow backend.\n","name":"stderr"},{"output_type":"stream","text":"WARNING:tensorflow:From /opt/conda/lib/python3.6/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.\nInstructions for updating:\nColocations handled automatically by placer.\nDownloading data from https://github.com/fchollet/deep-learning-models/releases/download/v0.1/vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5\n58892288/58889256 [==============================] - 2s 0us/step\n_________________________________________________________________\nLayer (type)                 Output Shape              Param #   \n=================================================================\ninput_1 (InputLayer)         (None, 80, 80, 3)         0         \n_________________________________________________________________\nblock1_conv1 (Conv2D)        (None, 80, 80, 64)        1792      \n_________________________________________________________________\nblock1_conv2 (Conv2D)        (None, 80, 80, 64)        36928     \n_________________________________________________________________\nblock1_pool (MaxPooling2D)   (None, 40, 40, 64)        0         \n_________________________________________________________________\nblock2_conv1 (Conv2D)        (None, 40, 40, 128)       73856     \n_________________________________________________________________\nblock2_conv2 (Conv2D)        (None, 40, 40, 128)       147584    \n_________________________________________________________________\nblock2_pool (MaxPooling2D)   (None, 20, 20, 128)       0         \n_________________________________________________________________\nblock3_conv1 (Conv2D)        (None, 20, 20, 256)       295168    \n_________________________________________________________________\nblock3_conv2 (Conv2D)        (None, 20, 20, 256)       590080    \n_________________________________________________________________\nblock3_conv3 (Conv2D)        (None, 20, 20, 256)       590080    \n_________________________________________________________________\nblock3_pool (MaxPooling2D)   (None, 10, 10, 256)       0         \n_________________________________________________________________\nblock4_conv1 (Conv2D)        (None, 10, 10, 512)       1180160   \n_________________________________________________________________\nblock4_conv2 (Conv2D)        (None, 10, 10, 512)       2359808   \n_________________________________________________________________\nblock4_conv3 (Conv2D)        (None, 10, 10, 512)       2359808   \n_________________________________________________________________\nblock4_pool (MaxPooling2D)   (None, 5, 5, 512)         0         \n_________________________________________________________________\nblock5_conv1 (Conv2D)        (None, 5, 5, 512)         2359808   \n_________________________________________________________________\nblock5_conv2 (Conv2D)        (None, 5, 5, 512)         2359808   \n_________________________________________________________________\nblock5_conv3 (Conv2D)        (None, 5, 5, 512)         2359808   \n_________________________________________________________________\nblock5_pool (MaxPooling2D)   (None, 2, 2, 512)         0         \n_________________________________________________________________\nglobal_average_pooling2d_1 ( (None, 512)               0         \n=================================================================\nTotal params: 14,714,688\nTrainable params: 14,714,688\nNon-trainable params: 0\n_________________________________________________________________\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras import layers\nfrom keras import models\nmodel = models.Sequential()\nmodel.add(vgg_model)\nmodel.add(layers.Dense(256, activation  = 'relu'))\nmodel.add(layers.Dense(1, activation = 'sigmoid'))","execution_count":8,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.summary()","execution_count":9,"outputs":[{"output_type":"stream","text":"_________________________________________________________________\nLayer (type)                 Output Shape              Param #   \n=================================================================\nvgg16 (Model)                (None, 512)               14714688  \n_________________________________________________________________\ndense_1 (Dense)              (None, 256)               131328    \n_________________________________________________________________\ndense_2 (Dense)              (None, 1)                 257       \n=================================================================\nTotal params: 14,846,273\nTrainable params: 14,846,273\nNon-trainable params: 0\n_________________________________________________________________\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras import backend as K\nK.set_image_dim_ordering('th')\nK.set_image_data_format('channels_last')\nfrom keras import layers\nfrom keras import models\nfrom keras import optimizers\nfrom keras.layers import GlobalAveragePooling2D\n\nmodel.compile(loss='binary_crossentropy',optimizer=optimizers.adam(lr=1e-4),metrics=['acc'])\n","execution_count":10,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_history=model.fit(train_data, train_label,validation_data=(valid_data,valid_label),epochs=20, batch_size=BATCH_SIZE)","execution_count":13,"outputs":[{"output_type":"stream","text":"Train on 20000 samples, validate on 5000 samples\nEpoch 1/20\n20000/20000 [==============================] - 44s 2ms/step - loss: 0.0956 - acc: 0.9621 - val_loss: 0.1280 - val_acc: 0.9484\nEpoch 2/20\n20000/20000 [==============================] - 44s 2ms/step - loss: 0.0718 - acc: 0.9713 - val_loss: 0.1719 - val_acc: 0.9380\nEpoch 3/20\n20000/20000 [==============================] - 44s 2ms/step - loss: 0.0493 - acc: 0.9823 - val_loss: 0.1614 - val_acc: 0.9378\nEpoch 4/20\n20000/20000 [==============================] - 44s 2ms/step - loss: 0.0378 - acc: 0.9860 - val_loss: 0.1379 - val_acc: 0.9544\nEpoch 5/20\n20000/20000 [==============================] - 44s 2ms/step - loss: 0.0316 - acc: 0.9888 - val_loss: 0.1594 - val_acc: 0.9548\nEpoch 6/20\n20000/20000 [==============================] - 44s 2ms/step - loss: 0.0334 - acc: 0.9884 - val_loss: 0.2819 - val_acc: 0.9304\nEpoch 7/20\n20000/20000 [==============================] - 44s 2ms/step - loss: 0.0233 - acc: 0.9923 - val_loss: 0.1780 - val_acc: 0.9444\nEpoch 8/20\n20000/20000 [==============================] - 44s 2ms/step - loss: 0.0215 - acc: 0.9926 - val_loss: 0.2277 - val_acc: 0.9448\nEpoch 9/20\n20000/20000 [==============================] - 44s 2ms/step - loss: 0.0214 - acc: 0.9925 - val_loss: 0.2077 - val_acc: 0.9512\nEpoch 10/20\n20000/20000 [==============================] - 44s 2ms/step - loss: 0.0232 - acc: 0.9918 - val_loss: 0.1915 - val_acc: 0.9356\nEpoch 11/20\n20000/20000 [==============================] - 44s 2ms/step - loss: 0.0186 - acc: 0.9938 - val_loss: 0.1791 - val_acc: 0.9482\nEpoch 12/20\n20000/20000 [==============================] - 44s 2ms/step - loss: 0.0173 - acc: 0.9947 - val_loss: 0.2453 - val_acc: 0.9572\nEpoch 13/20\n20000/20000 [==============================] - 44s 2ms/step - loss: 0.0182 - acc: 0.9942 - val_loss: 0.2306 - val_acc: 0.9506\nEpoch 14/20\n20000/20000 [==============================] - 44s 2ms/step - loss: 0.0170 - acc: 0.9944 - val_loss: 0.3140 - val_acc: 0.9368\nEpoch 15/20\n20000/20000 [==============================] - 44s 2ms/step - loss: 0.0135 - acc: 0.9957 - val_loss: 0.1632 - val_acc: 0.9538\nEpoch 16/20\n20000/20000 [==============================] - 44s 2ms/step - loss: 0.0152 - acc: 0.9948 - val_loss: 0.3107 - val_acc: 0.9236\nEpoch 17/20\n20000/20000 [==============================] - 44s 2ms/step - loss: 0.0157 - acc: 0.9950 - val_loss: 0.3181 - val_acc: 0.9510\nEpoch 18/20\n20000/20000 [==============================] - 44s 2ms/step - loss: 0.0139 - acc: 0.9952 - val_loss: 0.2263 - val_acc: 0.9416\nEpoch 19/20\n20000/20000 [==============================] - 44s 2ms/step - loss: 0.0130 - acc: 0.9959 - val_loss: 0.2452 - val_acc: 0.9496\nEpoch 20/20\n20000/20000 [==============================] - 44s 2ms/step - loss: 0.0114 - acc: 0.9959 - val_loss: 0.2295 - val_acc: 0.9514\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"import matplotlib.pyplot as plt\nacc = train_history.history['acc']\nval_acc = train_history.history['val_acc']\nloss = train_history.history['loss']\nval_loss = train_history.history['val_loss']\nepochs = range(1, len(acc) + 1)\nplt.plot(epochs, acc, 'blue', label='Training acc')\nplt.plot(epochs, val_acc, 'red', label='Validation acc')\nplt.title('Training and validation accuracy')\nplt.legend()\nplt.figure()\nplt.plot(epochs, loss, 'blue', label='Training loss')\nplt.plot(epochs, val_loss, 'red', label='Validation loss')\nplt.title('Training and validation loss')\nplt.legend()\nplt.show()","execution_count":15,"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 432x288 with 1 Axes>","image/png":"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\n"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"<Figure size 432x288 with 1 Axes>","image/png":"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\n"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras import Sequential\nfrom keras.layers import *\nimport keras.optimizers as optimizers\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.callbacks import *\nimport keras.backend as K\ntest_datagen = ImageDataGenerator(rescale=1./255)\n\ntest_generator = test_datagen.flow_from_directory(\"../input/test1\",target_size=(80, 80),batch_size=32,class_mode='binary')","execution_count":16,"outputs":[{"output_type":"stream","text":"Found 12500 images belonging to 1 classes.\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"from tensorflow.python.keras.models import Sequential\nfrom keras.models import load_model\n\nprint(\"-- Evaluate --\")\n\nscores = model.evaluate_generator(\n            test_generator, \n            steps = 100)\n","execution_count":17,"outputs":[{"output_type":"stream","text":"-- Evaluate --\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"Y_pred = model.predict(valid_data)\npredicted_label=np.round(Y_pred,decimals=2)","execution_count":18,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import matplotlib.pyplot as plt\n%matplotlib inline\nfrom mlxtend.plotting import plot_confusion_matrix\n\n# Get the confusion matrix\n\nCM = confusion_matrix(valid_label, Y_pred.round())\nfig, ax = plot_confusion_matrix(conf_mat=CM ,  figsize=(12, 12))\nplt.xticks(range(2), ['Cat', 'Dog'], fontsize=16)\nplt.yticks(range(2), ['Cat', 'Dog'], fontsize=16)\nplt.show()","execution_count":19,"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 864x864 with 1 Axes>","image/png":"iVBORw0KGgoAAAANSUhEUgAAAtMAAALCCAYAAAAcfl8PAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDMuMC4zLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvnQurowAAIABJREFUeJzt3Xm0pFV97+HvD5BRBFqQSeYg4MQoghAjCDhxIyIQBg3IGEXEGXFCryRGQYOIohhvQFFAJEI0iCACCorNIIMSQQyT0CCDA2NjN/v+UdWkaXs47PQ5p488z1q96pyqXVW/WsvVfHx71/tWay0AAMCTt9B4DwAAABOVmAYAgE5iGgAAOolpAADoJKYBAKCTmAYAgE5iGgAAOolpAADoJKYBAKDTIuM9wHioRZZotejS4z0GwAJj4w1WH+8RABYot9xyc+65556a17qnZkwvunQWW2+38R4DYIFxyU+PG+8RABYoW714sxGts80DAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATuMW01W1ZVV9o6ruqKpHq+reqjqvqvauqoWfxOvsVFXvHM1ZAQBgdsYlpqvq7UkuSTIpyWFJtkuyb5IbkhyfZMcn8XI7JRHTLBCeveKyOeeEt+XKMz6QK775gRy8x8ue8Pihb9w2D//suDxz2aWSJLu/arNMPu3wXPaN9+eCE9+ZFzxn1cfXHrzHy3L56e/PFd/8QN665xNfB+AvwbHH/Es22fB52XSj5+fv37BHHnnkkVx4wQ+y5Ys2yaYbPT/7v2nvTJs2bbzHhLka85iuqpcm+XSS41pr27XWvtpa+2Fr7azW2sFJXpDkprGeC+aHadMfy/s+/e/Z5PX/mL/5+6Nz0N+9NOuvvVKSQWi/fIsNcuuU+x5ff/Md92aH/Y/Ji3b7p3z8S+fkcx/cI0ny3HVWzpt2fkn++o1HZfO/+3he9dLnZ+3Vlh+XzwQwGm6//fZ8/nPH5pJLL88VV/0806dPz2mnfD3777t3vvK1U3PFVT/P6muskZO/ctJ4jwpzNR5Hpg9Lcl+S987uwdbar1tr11TVClX1xaq6oaoeqqrbqurrVfX4obuqOjHJ3klWrao2/HPzWHwImJ077/ljrvrlb5IkDzw0Nb+86c6sssKySZJPvvv1+cBnzkxr7fH1l159U35//8NJksnX3JRVVxysXX+tlXLZz2/Ow4/8KdOnP5YfXXFjdtp2ozH+NACja9q0aXn44YcHtw89lCWXWiqLLrpo1n3Oc5Ik2263fc781hnjPCXM3ZjG9HAv9DZJzm2tPTKP5ZOSPJLk8CSvTPKeJOsmuaSqFh+u+ViSs5PcnWTL4Z/XjcLo8KStvvKkbLTes3PZz2/Oji97Qe747e9z7Q23z3H9Pju9JN+75LokyS9+fUe22vivMmmZpbLE4k/LK7d+Xp690nJjNTrAqFt11VXz9ne8O89Ze/WstdrKecYzlskuu+6WadOm5YrLL0+SfOuMb+Y3t902zpPC3C0yxu+3fJIlktwyr4WtteuTHDrj92GIX5Lk1iSvSvKt1tqvq+ruJI+21i4dnZHhyVtqiUVzytH75z1Hn5Fp06fnvfu+Iju+5bg5rn/pZutm7522zMv3/ZckyfU33ZVPnXhevv35g/PQI4/m6ut/k+nTHxur8QFG3e9+97t859tn5b9+dVOWXXbZ7Ln7rjn161/LV04+Ne999zsyderUbLf9Dll44RGfkwDGxVjH9JNSVW9O8g9J1kmy1EwPrdfxWgcmOTBJ8rSnz4/xYLYWWWShnHL0ATntu5fnrB9cnef91SpZY9VnZvJphydJVn3WsvnJ1w/LX7/xqNx17/15/rqr5PgP75nXvvX43PeHBx9/nZPO/ElOOvMnSZKPvvX/5Pa7fj8unwdgNPzg/O9nzTXXygorrJAk2WmnnXPpT36cPfZ6Q86/8EdJku+fd25+9asbxnNMmKex3jN9b5KHk6wxr4VVdUiSzyf5fpKdk2yeZIvhw4vP6Xlz0lo7obW2WWtts1pkiSf7dBixLxyxV66/6c4ce/IPkiS/uPGOrPHyw7P+a47I+q85Irf/9vfZcs9P5K57789qKy2XU48+IPt96Cu58dbfPuF1Vlhu8H/6Vltpubx22w1z2ncvH/PPAjBaVltt9UyefGkeeuihtNZywQ/Oz3rrb5Df/nbwd+HUqVPzqaM+kQMO/IdxnhTmbkyPTLfWplXVhUm2r6rFWmtT57J89yTnt9beNeOOqlprtGeE/42XbLR29trxxbn2httz6anvS5Iccdx/5HsXXzfb9Ycf+KpMWnapHHP43yUZnA1k670+mSQ55ej9M2nZpfKnadPz9n/+Rv7wwMNj8yEAxsDmL35xXrfzLtly802yyCKLZMMNN85+BxyYj3z4g/nu2d/JY489lgMOfHNets224z0qzFXNfGaBMXnDwanxLkzy2dbaobN5fK0kSyc5KcmdrbVXzfTY/03yoSQfba19ZHjfF5Ps0lp75khnWGjJZ7XF1tvtf/MxAP6i/O6yOe/pB3gq2urFm+WKKy6vea0b8z3TrbUfDq9Y+Omqem6SEzP4UuFySV6eZP8keyY5J8lhVfX+JJOTbJtkl9m85HVJJg33V1+e5JHW2rWj/kEAAHjKG5cvILbWjqmqyUnekeToDM7ycX8GMXxQkm8nOTfJssM1iye5KMkrkvz3LC/3rxnspf6n4fpbkqw56h8CAICnvHE7m0dr7cdJfjyXJQ8nefPwz8yecLi9tfZgkj3m73QAADBv43EFRAAA+IsgpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoJOYBgCATmIaAAA6iWkAAOgkpgEAoNMic3qgqu5P0mb8Orxtw59ba+0ZozwbAAAs0OYY0621pcdyEAAAmGhGtM2jqrauqjcNf16+qtYa3bEAAGDBN8+YrqojkhyW5PDhXYsmOXk0hwIAgIlgJEemX5fkb5M8mCSttTuS2AICAMBT3khi+tHWWsvwy4hVtdTojgQAABPDSGL6G1X1xSTLVtUBSb6f5EujOxYAACz45ng2jxlaa0dX1fZJ/pjkOUk+3Fo7b9QnAwCABdw8Y3ro2iRLZLDV49rRGwcAACaOkZzNY/8kk5PsnGSXJJdW1b6jPRgAACzoRnJk+j1JNm6t3ZskVfXMJD9O8v9GczAAAFjQjeQLiPcmuX+m3+8f3gcAAE9pczwyXVXvHP54Y5KfVtVZGeyZfm2Sa8ZgNgAAWKDNbZvHjAuz/Hr4Z4azRm8cAACYOOYY0621j47lIAAAMNHM8wuIVbVCkvcmeV6SxWfc31rbdhTnAgCABd5IvoD4tSS/TLJWko8muTnJZaM4EwAATAgjielntta+nORPrbWLWmv7JnFUGgCAp7yRnGf6T8PbKVX1miR3JJk0eiMBAMDEMJKYPrKqlknyriSfTfKMJO8Y1akAAGACmGdMt9a+M/zxD0m2Gd1xAABg4pjbRVs+m8FFWmartfa2UZloDGy4weq56JJjx3sMgAXGci/74HiPALBAmXr97SNaN7cj05fPn1EAAOAv09wu2nLSWA4CAAATzUhOjQcAAMyGmAYAgE5iGgAAOs0zpqvqOVV1flX9fPj7C6vK174BAHjKG8mR6S8lOTzDKyG21q5JsvtoDgUAABPBSGJ6ydba5FnumzYawwAAwEQykpi+p6rWyfACLlW1S5IpozoVAABMAPO8nHiSg5OckGT9qro9yU1J3jCqUwEAwAQwz5hurf13ku2qaqkkC7XW7h/9sQAAYME3z5iuqg/P8nuSpLX2f0dpJgAAmBBGss3jwZl+XjzJjkn+a3TGAQCAiWMk2zw+NfPvVXV0ku+N2kQAADBB9FwBcckkz57fgwAAwEQzkj3T12Z4WrwkCydZIYn90gAAPOWNZM/0jjP9PC3JXa01F20BAOApb64xXVULJ/lea239MZoHAAAmjLnumW6tTU9yfVWtPkbzAADAhDGSbR7LJflFVU3OTKfJa6397ahNBQAAE8BIYvpDoz4FAABMQCOJ6Ve31g6b+Y6q+kSSi0ZnJAAAmBhGcp7p7Wdz36vm9yAAADDRzPHIdFW9OclbkqxdVdfM9NDSSS4Z7cEAAGBBN7dtHl9P8t0kH0/yvpnuv7+1dt+oTgUAABPAHGO6tfaHJH9IssfYjQMAABPHSPZMAwAAsyGmAQCgk5gGAIBOYhoAADqJaQAA6CSmAQCgk5gGAIBOYhoAADqJaQAA6CSmAQCgk5gGAIBOYhoAADqJaQAA6CSmAQCgk5gGAIBOYhoAADqJaQAA6CSmAQCgk5gGAIBOYhoAADqJaQAA6CSmAQCgk5gGAIBOYhoAADqJaQAA6CSmAQCgk5gGAIBOYhoAADqJaQAA6CSmAQCgk5gGAIBOYhoAADqJaQAA6CSmAQCgk5gGAIBOYhoAADqJaQAA6CSmAQCgk5gGAIBOYhoAADqJaQAA6CSmAQCgk5gGAIBOYhoAADqJaQAA6CSmAQCgk5gGAIBOYhoAADqJaQAA6CSmAQCgk5gGAIBOYhoAADqJaQAA6CSmAQCgk5gGAIBOYhoAADqJaQAA6CSmAQCgk5gGAIBOYhoAADqJaQAA6CSmAQCgk5gGAIBOYhoAADqJaQAA6CSmAQCgk5gGAIBOYhoAADqJaQAA6CSmAQCgk5gGAIBOYhoAADqJaQAA6CSmAQCgk5gGAIBOYhoAADqJaQAA6CSmAQCgk5gGAIBOYhoAADqJaQAA6CSmAQCgk5gGAIBOYhoAADqJaQAA6CSmAQCgk5gGAIBOYhoAADqJaQAA6CSmAQCgk5gGAIBOYhoAADqJaQAA6CSmAQCgk5gGAIBOYhoAADqJaQAA6CSmAQCgk5gGAIBOYhoAADqJaQAA6CSmAQCgk5gGAIBOYhoAADqJaQAA6CSmAQCgk5gGAIBOYhoAADqJaQAA6CSmAQCgk5gGAIBOYhoAADqJaQAA6CSmAQCgk5gGAIBOYhoAADqJaQAA6CSmAQCgk5gGAIBOYhoAADqJaQAA6CSmAQCgk5gGAIBOYhoAADqJaQAA6CSmAQCgk5gGAIBOYhoAADqJaQAA6CSmAQCgk5gGAIBOoxrTVbVPVbWZ/jxYVTdX1beqareqqtF8fwAAGE1jdWR61yRbJnl1kg8lmZrklCTnVdUSYzQDjKmDD9ov66y+UrbY9IWP3/fxIz+a9ddeLVu/eJNs/eJNcu45Zz/hObfdemtWWf4ZOfZfPjXW4wKMimc/a5mcc+y+ufKrb8sVXz0kB++6ZZLkw/u/PJNPfGsu/beD8+1P75OVn7l0kmT37TfM5BPfmstOemsuOP7AvOCvVnr8tQ7Z7SW54quH5PKvHJKTPrJbFlt0kXH5TDCzsYrpq1prl7bWLmqtfbW1tnuS3ZJsm+STYzQDjKk937h3zjjr7D+7/y2HvD0X//TKXPzTK7PDK1/9hMfef9i7st0OrxyrEQFG3bTp0/O+476bTd54bP7mwC/moJ1fnPXXXCH/8vWLs/k+x2WLN30u3/3xL3P4m7ZJktw85b7scMi/5kV7H5ePn3RBPvfe1yZJVll+6bxlly2z1X7HZ7O//2wWXqiy68tfMJ4fDZKM457p1toZSc5KckBVLZkkVbVyVX2lqu6pqqlVdU1VvWHW51bVdlX1s6p6pKpurKr9q+rEqrp5jD8GzNFWW780y02aNOL13/mPM7PGmmtlg+c+bxSnAhhbd977QK66YUqS5IGHH80vb747qyz/jNz/0NTH1yy5+KJprSVJLv35bfn9/Y8kSSb/4rasusIyj69bZOGFssRiT8vCw9sp99w/hp8EZm+8v4B4dpLFkmxWVUsluSjJq5K8P8lOSa5N8tWqOnDGE6rquUn+M8kDSXYfrj00g6PcsMD70hc+l5e8aKMcfNB++d3vfpckeeCBB3LMp47K+z7w4XGeDmD0rL7SstnoOSvnsut+kyT5yIHb5VdnvCe777BhPvbl8/9s/T47bprvXXpDkuSOe+7PMadenBvOeHduOvOw/PHBqTn/shvHdH6YnfGO6VuHtysneVOSdZPs2lo7obX23dbaXknOT3JkVS08XPvBJH9M8orW2pmttW8k2SHJs8Z4dnjS9jvgH3LVdb/KxT+9MiuutHI++L53JxnspX7LIYfm6U9/+jhPCDA6llpi0Zzyj3vkPZ85+/Gj0h854ftZ9/VH5dRzr84/7LzFE9a/dOO1svdrNs0Hj/9ekmTZpRfPjltvkA12+1TW3ukTWWrxp2X3HTYc888BsxrvmJ5xNo+W5KVJbm+tXTjLmpOTrJDkucPft0hydmvtoRkLWmtTkvx4rm9UdWBVXV5Vl997993zY3Z40p614opZeOGFs9BCC2XvfffPFZdfliS54rLJOeID78sL1ls7xx/3mXzqqI/nhOM/N87TAswfiyy8UE45co+cdu7VOeuH1/3Z46edd3V2etn/bHF7/jor5vj3vS67Hv613PfHh5Mk2262Tm6e8rvc8/uHMm36Yznzh9dlixesPmafAeZkvL8Gu9rwdkqSScPbWd05vJ2x+XTlJL+dzbq7kqw9pzdqrZ2Q5IQk2XjTzVrPsPC/deeUKVlp5ZWTJN8568zH90efc/5Fj6/5+JEfzVJLPT0HvvngcZkRYH77wuGvy/W33J1jT/uf417rPPuZ+fVv7k2S7Lj1BrnhlsGBrtVWXCan/uOe2e9jp+fG2+59fP1td/0hmz/v2Vlisafl4al/yjabrpMrf3n72H4QmI3xjunXJHkkyRVJ7kuy3mzWzDgnzn3D2ymZ/ZaOFef7dPC/sO/f75mLf3RR7r3nnmywzuo5/ENH5OIfXpRrr7k6VZXV11gjx3z2C+M9JsCoeskL18her9w41954Zy79t8FBgiO+eF722XHTrLv68nnssZZb7/p93nbUWUmSw/fZJpOWWTLHvOtvkyTTpj+Wrfc/Ppdd95t864Jf5Cf/7y2ZNv2xXH3DlHz5Py4bt88FM9SMb8+OyotX7ZPk35Ks21q7cZbHXp/k9CSfaa29o6oOTnJckq1ba5fMtO7cJBsmWaW1Nr2qvp5k+yRrzNjqUVUrJ7k5yZTW2przmmvjTTdrF10yeT58QoC/DCtu58uvADObetWX89gDU+Z5gcGxOjK9UVUtn2TRJKsn2TGDC7mcl+Tw4ZoTMzgrx79X1QeS/CbJXhmE80GttenDdUcm2SXJ96rq6AzOBvKhDLZ5PDYmnwYAADJ2MX368PaRDPY7X5nBae2+2YaHxltrD1bV32RwEZd/TrJ0kuuTvLG1dvKMF2qtXVdVr0lyVJJvJLk9ySeSvDLJmmPyaQAAIKMc0621EzM44jzS9VOSvHEE685LstGM36vq6Uk+msH5pwEAYEyM9xcQu1TVZzM4Fd4dSVbJYHvIckk+M55zAQDw1DIhYzrJ4hls7VgxyaNJJifZrrV2zbhOBQDAU8qEjOnW2gHjPQMAAIz3FRABAGDCEtMAANBJTAMAQCcxDQAAncQ0AAB0EtMAANBJTAMAQCcxDQAAncQ0AAB0EtMAANBJTAMAQCcxDQAAncQ0AAB0EtMAANBJTAMAQCcxDQAAncQ0AAB0EtMAANBJTAMAQCcxDQAAncQ0AAB0EtMAANBJTAMAQCcxDQAAncQ0AAB0EtMAANBJTAMAQCcxDQAAncQ0AAB0EtMAANBJTAMAQCcxDQAAncQ0AAB0EtMAANBJTAMAQCcxDQAAncQ0AAB0EtMAANBJTAMAQCcxDQAAncQ0AAB0EtMAANBJTAMAQCcxDQAAncQ0AAB0EtMAANBJTAMAQCcxDQAAncQ0AAB0EtMAANBJTAMAQCcxDQAAncQ0AAB0EtMAANBJTAMAQCcxDQAAncQ0AAB0EtMAANBJTAMAQCcxDQAAncQ0AAB0EtMAANBJTAMAQCcxDQAAncQ0AAB0EtMAANBJTAMAQCcxDQAAncQ0AAB0EtMAANBJTAMAQCcxDQAAncQ0AAB0EtMAANBJTAMAQCcxDQAAncQ0AAB0EtMAANBJTAMAQCcxDQAAncQ0AAB0EtMAANBJTAMAQCcxDQAAncQ0AAB0EtMAANBJTAMAQCcxDQAAncQ0AAB0EtMAANBJTAMAQCcxDQAAncQ0AAB0EtMAANBJTAMAQCcxDQAAncQ0AAB0EtMAANBJTAMAQCcxDQAAncQ0AAB0EtMAANBJTAMAQCcxDQAAncQ0AAB0EtMAANBJTAMAQCcxDQAAncQ0AAB0EtMAANBJTAMAQCcxDQAAncQ0AAB0EtMAANBJTAMAQCcxDQAAncQ0AAB0EtMAANBJTAMAQCcxDQAAncQ0AAB0EtMAANBJTAMAQCcxDQAAncQ0AAB0EtMAANBJTAMAQCcxDQAAncQ0AAB0EtMAANBJTAMAQCcxDQAAncQ0AAB0EtMAANBJTAMAQCcxDQAAncQ0AAB0EtMAANBJTAMAQCcxDQAAncQ0AAB0EtMAANBJTAMAQCcxDQAAncQ0AAB0EtMAANBJTAMAQCcxDQAAncQ0AAB0EtMAANBJTAMAQCcxDQAAncQ0AAB0qtbaeM8w5qrq7iS3jPcckGT5JPeM9xAACxB/L7KgWKO1tsK8Fj0lYxoWFFV1eWtts/GeA2BB4e9FJhrbPAAAoJOYBgCATmIaxtcJ4z0AwALG34tMKPZMAwBAJ0emAQCgk5iGUVBVW1bVN6rqjqp6tKrurarzqmrvqlr4SbzOTlX1ztGcFWB+q6p9qqrN9OfBqrq5qr5VVbtVVY33jDC/iGmYz6rq7UkuSTIpyWFJtkuyb5IbkhyfZMcn8XI7JRHTwES1a5Itk7w6yYeSTE1ySpLzqmqJ8RwM5pdFxnsA+EtSVS9N8ukkx7XW3jbLw2dV1aeTLDX2kwGMi6taazfO9PtXq+r0JKcn+WSSQ8ZnLJh/HJmG+euwJPclee/sHmyt/bq1dk1VrVBVX6yqG6rqoaq6raq+XlWrzlhbVScm2TvJqjP9U+nNY/EhAEZLa+2MJGclOaCqlkySqlq5qr5SVfdU1dSquqaq3jDrc6tqu6r6WVU9UlU3VtX+VXWivxsZT45Mw3wy3Au9TZIzW2uPzGP5pCSPJDk8yd1JVknyriSXVNX6w+d/LMkKSV6U5G+Hz5s6GrMDjLGzM9jGtllVXZHkoiTLJXl/ktuSvCGDo9hLttZOSJKqem6S/0wyOcmdh6WeAAAGgklEQVTuSRbNYOvIMkkeG/NPAENiGuaf5ZMskeSWeS1srV2f5NAZvw9D/JIktyZ5VZJvtdZ+XVV3J3m0tXbp6IwMMC5uHd6unORNSdZNsk1r7cLh/d+tqhWTHFlVX26tTU/ywSR/TPKK1tpDSVJVP0pyU5I7x3J4mJltHjBOqurNVXV1VT2QZFr+5z8u643jWABjYcbZPFqSlya5faaQnuHkDP517rnD37dIcvaMkE6S1tqUJD8e3VFh7sQ0zD/3Jnk4yRrzWlhVhyT5fJLvJ9k5yeYZ/IciSRYfrQEBFhCrDW+nZLDtbcps1sw42jxpeLtykt/OZt1d83c0eHJs84D5pLU2raouTLJ9VS3WWpvb/ubdk5zfWnvXjDuqaq3RnhFgAfGaDL43ckUGX9qe3b/IrTS8vW94OyXJs2azbsX5Ph08CY5Mw/z1z0memcEpn/5MVa1VVS9MsmSSP83y8Jtm85SpGezDBviLUFWvz+BL1V8Ybtm4KMmzq2qrWZbumcGR6OuGv1+a5NUzzgAyfK2Vk8z6PBhTjkzDfNRa++HwioWfHn7z/MQM9kIvl+TlSfbP4D8Q5yQ5rKren8E307dNsstsXvK6JJOq6s1JLk/ySGvt2lH/IADzx0ZVtXwGZ95YPYOLVu2a5LwMzmaUDP6ePDTJv1fVB5L8JsleSbZPctDwy4dJcmQGf09+r6qOTrJYBmfzuCvO5sE4EtMwn7XWjqmqyUnekeToDM7ycX8GMXxQkm8nOTfJssM1i2dwZOYVSf57lpf71wz2Uv/TcP0tSdYc9Q8BMH+cPrx9JIOjzFdmsM3tm621liSttQer6m8y+Be9f06ydJLrk7yxtXbyjBdqrV1XVa9JclSSbyS5Pcknkrwy/l5kHNXwf8sAABNKVT09yY1J/rO1tt94z8NTkyPTAMCEUFWfzeBUeHdkcLGrQzPYRveZ8ZyLpzYxDQBMFItnsLVjxSSPZvCdk+1aa9eM61Q8pdnmAQAAnZwaDwAAOolpAADoJKYBAKCTmAaY4KrqgeHtKlX1zXmsffvMV5Ab4eu/rKq+M9L7Z1mzT1Ud9yTf7+bhhT4AFnhiGmABVFULP9nntNbuaK3N7kqaM3t7BpezB2A+ENMAY6iq1qyqX1bV16rqv6rqmzOOFA+PyH6iqq5MsmtVrVNV51TVFVX1o6paf7hurar6SVVdW1VHzvLaPx/+vHBVHV1VP6+qa6rqkKp6Wwbn5r2gqi4Yrtth+FpXVtXpw4tgpKpeOZzzyiQ7j+BzbT58nZ9V1Y+rar2ZHl6tqi6sql9V1REzPecNVTW5qq6qqi/2/B8IgPEmpgHG3npJPt9a2yDJH5O8ZabH7m2tbdJaOzXJCUkOaa1tmuTdST4/XPOZJMe31l6QZMoc3uPADC6xvFFr7YVJvtZaOzaDi11s01rbZriV4oMZnKd3kwwuef/Oqlo8yZeS/J8kmyZZaQSf6ZdJ/rq1tnGSDyf5p5ke2zzJ65O8MIP/k7BZVW2Q5O+SbNVa2yjJ9CR7jeB9ABYoLtoCMPZua61dMvz55CRvS3L08PfTkscvk/ySJKdX1YznLTa83SqDOE2Sr2ZwEYtZbZfkC621aUnSWrtvNmu2SPLcJJcM32PRJD9Jsn6Sm1prvxrOcnIGcT43yyQ5qarWTdKSPG2mx85rrd07fK1/T7J1kmkZhPplw/deIslv5/EeAAscMQ0w9ma9WtbMvz84vF0oye+HR21H8ho9KoPQ3eMJd1bN6T3n5mNJLmitva6q1kxy4UyPze7zVpKTWmuHd7wXwALDNg+Asbd6VW05/HnPJBfPuqC19sckN1XVrklSAxsOH74kye7Dn+e0NeK8JAdV1SLD508a3n9/kqWHP1+aZKuq+qvhmqWq6jkZbNlYs6rWGa57QmzPwTJJbh/+vM8sj21fVZOqaokkOw3nPz/JLlX1rBnzVdUaI3gfgAWKmAYYe9cnObiq/ivJckmOn8O6vZLsV1VXJ/lFktcO7z90+Pxrk6w6h+f+a5Jbk1wzfP6ew/tPSHJOVV3QWrs7g/A9paquyXCLR2vtkQy2dfzn8AuII9l+8ckkH6+qn+XP/9VzcpIzklyT5IzW2uWttesy2K997vC9z0uy8gjeB2CBUq3Nj38pBGAkhlsgvtNae/44jwLAfODINAAAdHJkGgAAOjkyDQAAncQ0AAB0EtMAANBJTAMAQCcxDQAAncQ0AAB0+v/SygUSQ0tcOAAAAABJRU5ErkJggg==\n"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.4","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}