{"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)\nimport matplotlib.pyplot as plt # data visualization\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 the files in the input directory\n\nimport os\nprint(os.listdir(\"../input\"))\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"# It will takes about 1 ~ 2 minutes (depends on CPU)\ntrain_data = np.genfromtxt('../input/train.csv', delimiter=',',\n                  skip_header=1).astype(np.dtype('uint8'))\nX_train = train_data[:,1:]\ny_train = train_data[:,:1]\n\nX_test = np.genfromtxt('../input/test.csv', delimiter=',',\n                  skip_header=1).astype(np.dtype('uint8'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"scrolled":false,"_uuid":"09c4742e11cd0388a3f44e762d52432a8b53f383"},"cell_type":"code","source":"m_train = X_train.shape[0]\nm_test = X_test.shape[0]\nprint(X_train.shape)\nprint(y_train.shape)\nprint(X_test.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"752d77bd28e3ae1841aec1d0771ad25d76eeb54c"},"cell_type":"code","source":"np.random.seed(0);\nindices = list(np.random.randint(m_train, size=9))\nfor i in range(9):\n    plt.subplot(3,3,i + 1)\n    plt.imshow(X_train[indices[i]].reshape(28,28), cmap='gray', interpolation='none')\n    plt.title(\"Index {} Class {}\".format(indices[i], y_train[indices[i]]))\n    plt.tight_layout()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"33dc4abbed4d3d1259be5309fb26574305014f1c"},"cell_type":"code","source":"def euclidean_distance(vector1, vector2):\n    return np.sqrt(np.sum(np.power(vector1 - vector2, 2)))\ndef absolute_distance(vector1, vector2):\n    return np.sum(np.absolute(vector1 - vector2))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"2026511dad2ded9ae476c156ef21e92d8f9fb55b"},"cell_type":"code","source":"import operator\ndef get_neighbours(X_train, test_instance, k):\n    distances = []\n    neighbors = []\n    for i in range(0, X_train.shape[0]):\n        dist = euclidean_distance(X_train[i], test_instance)\n        distances.append((i, dist))\n    distances.sort(key=operator.itemgetter(1))\n    for x in range(k):\n        # print(distances[x])\n        neighbors.append(distances[x][0])\n    return neighbors","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"f0331aaa12566702e8f47d2c12c4001c36e56dff"},"cell_type":"code","source":"def predictkNNClass(output, y_train):\n    classVotes = {}\n    for i in range(len(output)):\n    # print(output[i], y_train[output[i]])\n        if y_train[output[i]][0] in classVotes:\n            classVotes[y_train[output[i]][0]] += 1\n        else:\n            classVotes[y_train[output[i]][0]] = 1\n    sortedVotes = sorted(classVotes.items(), key=operator.itemgetter(1), reverse=True)\n    # print(sortedVotes)\n    return sortedVotes[0][0]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"e11722647b8c857a983da685fea1d1906139fd20"},"cell_type":"code","source":"instance_num = 0\nk = 9\nplt.imshow(X_test[instance_num].reshape(28,28), cmap='gray', interpolation='none')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"2d2ce88d8d6efb2073592bcee6a6b699b4f8ed3c"},"cell_type":"code","source":"instance_neighbours = get_neighbours(X_train, X_test[instance_num], 9)\nindices = instance_neighbours\nfor i in range(9):\n    plt.subplot(3,3,i + 1)\n    plt.imshow(X_train[indices[i]].reshape(28,28), cmap='gray', interpolation='none')\n    plt.title(\"Index {} Class {}\".format(indices[i], y_train[indices[i]]))\n    plt.tight_layout()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"78f3f960ed29b841cd83dc779b3dc6e550118171","scrolled":true},"cell_type":"code","source":"predictkNNClass(instance_neighbours, y_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"20d199790c3044fbf2ba772683c9a8882729040d"},"cell_type":"code","source":"import csv\nsubmit = pd.DataFrame(columns=('ImageId', 'Label'))\nfor i in range(5):  # change 5 to X_test.shapep[0] will takes a long long long ... TIME!\n    neighbours = get_neighbours(X_train, X_test[i], 20)\n    label = predictkNNClass(neighbours, y_train)\n    submit.loc[i]={'ImageId': i + 1,'Label': label}","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"874a1b9c36be7d97a9d0f4f248eeaacd28d8c7d8"},"cell_type":"code","source":"submit","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"f72f6514b3b47fa28c864836088f5ee61d7c010d"},"cell_type":"code","source":"submit.to_csv('csv_to_submit.csv', index = False)","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.6","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}