{"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\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 read-only \"../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\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 5GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train = pd.read_csv('/kaggle/input/digit-recognizer/train.csv')  \nprint(train.shape)\ntrain.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test= pd.read_csv(\"/kaggle/input/digit-recognizer/test.csv\")\nprint(test.shape)\ntest.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train = (train.iloc[:,1:].values).astype('float32') # all pixel values\nY_train = train.iloc[:,0].values.astype('int32') # only labels i.e targets digits\nX_test = test.values.astype('float32')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import matplotlib.pyplot as plt\n%matplotlib inline\n\n#Convert train datset to (num_images, img_rows, img_cols) format \nX_train = X_train.reshape(X_train.shape[0], 28, 28)\n\nfor i in range(0, 3):\n    plt.subplot(330 + (i+1))\n    plt.imshow(X_train[i], cmap=plt.get_cmap('gray'))\n    plt.title(Y_train[i]);\n    \nX_train = X_train.reshape(X_train.shape[0], -1) # Reflattens back the dataset","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train = X_train[0:38000]\ny_train = Y_train[0:38000]\nx_dev = X_train[38000:42000]\ny_dev = Y_train[38000:42000]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(x_train.shape)\nprint(y_train.shape)\nprint(x_dev.shape)\nprint(y_dev.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.neural_network import MLPClassifier\nimport time\n\nclf = MLPClassifier(solver='adam', alpha=0.5, hidden_layer_sizes=(400, 100, 50), random_state=1)\n\n# Training\ntic = time.time()\nclf.fit(x_train, y_train)\ntoc = time.time()\nprint(\"The total training time is\", toc-tic, \"seconds\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn import  metrics\n\n#accuracy and confusion matrix on the training set set\npredicted_train = clf.predict(x_train)\n\nprint(\"Classification report for classifier %s:\\n%s\\n\" % (clf, metrics.classification_report(y_train, predicted_train)))\nprint(\"Confusion matrix:\\n%s\" % metrics.confusion_matrix(y_train, predicted_train))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#accuracy and confusion matrix on the dev set\npredicted_dev = clf.predict(x_dev)\n\nprint(\"Classification report for classifier %s:\\n%s\\n\" % (clf, metrics.classification_report(y_dev, predicted_dev)))\nprint(\"Confusion matrix:\\n%s\" % metrics.confusion_matrix(y_dev, predicted_dev))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predictions = clf.predict(X_test)\nsubmissions=pd.DataFrame({\"ImageId\": list(range(1,len(predictions)+1)),\n                         \"Label\": predictions})\nsubmissions.to_csv(\"submissions.csv\", index=False, header=True)","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":4}