{"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 \n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfile_names=[]\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        file_names.append(os.path.join(dirname, filename))\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","collapsed":true,"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":false},"cell_type":"markdown","source":"### importting librariresd\n"},{"metadata":{"trusted":true},"cell_type":"code","source":"import tensorflow as tf\nimport pandas as pd\nimport matplotlib.pyplot as plt\nimport cv2","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train=pd.read_csv(file_names[1])\n# file_names","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train\nlabels=train[[\"label\"]]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"labels=labels.to_numpy()\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"labels","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train=train.iloc[:,1:]\ntrain.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"labels","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"raw","source":"train"},{"metadata":{"trusted":true},"cell_type":"code","source":"train=train.to_numpy()\ntrain.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"lis=[]\nfor i in range(0,42000):\n    lis.append(train[i].reshape(28,28,1))\nlis=np.array(lis)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"lis.shape\nlis_inverse=[]\nfor i in lis:\n    lis_inverse.append((i.T).reshape(28,28,1))\nfinal_set=[]\nfor i in lis:\n    final_set.append(i)\nfor i in lis_inverse:\n    final_set.append(i)\nfinal_set=np.array(final_set)\nfinal_set.shape\n# plt.imshow(final_set[12].reshape(28,28))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"final_label=[]\nfor i in labels:\n    final_label.append(i)\nfor i in labels:\n    final_label.append(i)\nfinal_label=np.array(final_label)\nfinal_label.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"labels.shape\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"labels[34]\n# labels are the correct present here yes\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"p.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# trying the custom model\nmodel=tf.keras.models.Sequential(\n[\n    tf.keras.layers.Conv2D(filters=128,kernel_size=3,input_shape=(28,28,1),activation=\"relu\"),\n    tf.keras.layers.MaxPool2D(pool_size=(3,3),strides=3,padding=\"same\"),\n    tf.keras.layers.Dropout(0.3),\n#     tf.keras.layers.Conv2D(filters=64,kernel_size=3,activation=\"relu\"),\n#     tf.keras.layers.MaxPool2D(pool_size=(3,3),strides=3,padding=\"same\"),\n#     tf.keras.layers.Dropout(0.3),\n    tf.keras.layers.Conv2D(filters=64,kernel_size=3,activation=\"relu\"),\n    tf.keras.layers.MaxPool2D(pool_size=(3,3),strides=3,padding=\"same\"),\n    tf.keras.layers.Dropout(0.2),\n    tf.keras.layers.Conv2D(filters=32,kernel_size=3,activation=\"relu\"),\n    tf.keras.layers.MaxPool2D(pool_size=(3,3),strides=3,padding=\"same\"),\n    tf.keras.layers.Dropout(0.2),\n#     tf.keras.layers.Conv2D(filters=32,kernel_size=3,activation=\"relu\"),\n#     tf.keras.layers.MaxPool2D(pool_size=(3,3),strides=3,padding=\"same\"),\n    tf.keras.layers.Flatten(),\n    tf.keras.layers.Dense(128,activation=\"relu\"),\n    tf.keras.layers.Dense(128,activation=\"relu\"),\n#     tf.keras.layers.Dropout(0.3),\n#     tf.keras.layers.Dense(128,activation=\"relu\"),\n#     tf.keras.layers.Dense(128,activation=\"relu\"),\n#     tf.keras.layers.Dropout(0.3),\n    tf.keras.layers.Dense(128,activation=\"relu\"),\n    tf.keras.layers.Dense(128,activation=\"relu\"),\n    tf.keras.layers.Dropout(0.3),\n    tf.keras.layers.Dense(128,activation=\"relu\"),\n    tf.keras.layers.Dense(64,activation=\"relu\"),\n    tf.keras.layers.Dropout(0.3),\n    tf.keras.layers.Dense(32,activation=\"relu\"),\n    tf.keras.layers.Dense(10,activation=\"softmax\")\n])\n# # coustom model does not do well here\n# model=tf.keras.applications.InceptionV3(weights=\"imagenet\")\n# model.trainable=False\n# model=tf.keras.layers.Sequential([\n#     model,\n#     tf.keras.layers.Dense(128,activation=\"relu\",input_shape=(10,)),\n#     tf.keras.layers.Dense(10,activation=\"softmax\")\n# ])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from tensorflow.keras.layers import Conv2D,BatchNormalization,Dropout,Flatten,Dense\nmodel = tf.keras.Sequential()\n\nmodel.add(Conv2D(32,kernel_size=3,activation='relu',input_shape=(28,28,1)))\nmodel.add(BatchNormalization())\nmodel.add(Conv2D(32,kernel_size=3,activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(Conv2D(32,kernel_size=5,strides=2,padding='same',activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(Dropout(0.4))\n\nmodel.add(Conv2D(64,kernel_size=3,activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(Conv2D(64,kernel_size=3,activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(Conv2D(64,kernel_size=5,strides=2,padding='same',activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(Dropout(0.4))\n\nmodel.add(Flatten())\nmodel.add(Dense(128, activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(Dropout(0.4))\nmodel.add(Dense(10, activation='softmax'))\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(loss=\"sparse_categorical_crossentropy\",optimizer=\"sgd\",metrics=[\"accuracy\"])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# labels.shape\n# lis.shape\nmodel.fit(final_set,final_label,epochs=45,batch_size=200)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# model2=model\n# model2.compile(loss=\"sparse_categorical_crossentropy\",optimizer=\"sgd\",metrics=[\"accuracy\"])\nfile_names\ntest=pd.read_csv(file_names[2])\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\ntest=test.to_numpy()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"lis=[]\nfor i in range(0,28000):\n    lis.append(test[i].reshape(28,28,1))\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"lis=np.array(lis)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.evaluate(final_set[32:6787],final_label[32:6787])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"answer=model.predict(lis)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"answers=[]\nfor i in answer:\n    answers.append(np.argmax(i))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"answers=np.array(answers)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"answers=pd.Series(answers)\nImageId=[]\nfor i in range(1,28001):\n    ImageId.append(i)\nImageId=pd.Series(ImageId)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Submission=pd.DataFrame(data={\"ImageId\":ImageId,\"Label\":answers})\nSubmission.index+=1\nSubmission","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from IPython.display import HTML\nimport pandas as pd\nimport numpy as np\ndf = Submission\n\ndf.to_csv('this_submission.csv',index=False)\n\ndef create_download_link(title = \"Download CSV file\", filename = \"data.csv\"):  \n    html = '<a href={filename}>{title}</a>'\n    html = html.format(title=title,filename=filename)\n    return HTML(html)\n\n# create a link to download the dataframe which was saved with .to_csv method\ncreate_download_link(filename='this_submission.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(\"hello\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":1}