{"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\n#Imports\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 # visualization\n\nfrom tensorflow import keras\nimport tensorflow as tf\n#The first method I attempt to use; a simple neural network.\n\nfrom sklearn.neighbors import KNeighborsClassifier\n# The second method I attempt to use; k-neighbors classifier.\n\nfrom sklearn.ensemble import RandomForestClassifier\n# The third method I attempt to use; random forest classifier.\n\n\n\n\n\n\n\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\"))\ntest = pd.read_csv('../input/test.csv')\ntrain = pd.read_csv('../input/train.csv')\n\n\n\n# Any results you write to the current directory are saved as output.","execution_count":77,"outputs":[{"output_type":"stream","text":"['sample_submission.csv', 'test.csv', 'train.csv']\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import train_test_split\ntraining_size = 5000\nX_train, X_test, y_train, y_test = train_test_split(train.drop('label', axis = 1)[:training_size], train['label'][:training_size], random_state = 0)","execution_count":102,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Neural Network\n\nlayers = keras.layers\n#print(X_train.iloc[0])\n#print(X_train.values)\nnX_train = keras.utils.normalize(X_train.values, axis = 1)\nnX_test = keras.utils.normalize(X_test.values, axis = 1)\nmodel = keras.models.Sequential()\nmodel.add(keras.layers.Flatten())\nmodel.add(keras.layers.Dense(128, activation = tf.nn.relu))\nmodel.add(keras.layers.Dense(128, activation = tf.nn.relu))\nmodel.add(keras.layers.Dense(128, activation = tf.nn.relu))\nmodel.add(keras.layers.Dense(128, activation = tf.nn.relu))\nmodel.add(keras.layers.Dense(10, activation = tf.nn.softmax))\n\nmodel.compile(optimizer = 'sgd',\n loss='sparse_categorical_crossentropy',\n metrics = ['accuracy'])\n#keras.optimizers.SGD(lr=0.01, momentum=0.0, decay=0.0, nesterov=False)\nmodel.fit(nX_train, y_train.values, epochs = 5)","execution_count":93,"outputs":[{"output_type":"stream","text":"Epoch 1/5\n3750/3750 [==============================] - 1s 332us/sample - loss: 2.2970 - acc: 0.1891\nEpoch 2/5\n3750/3750 [==============================] - 1s 178us/sample - loss: 2.2882 - acc: 0.2749\nEpoch 3/5\n3750/3750 [==============================] - 1s 181us/sample - loss: 2.2794 - acc: 0.2893\nEpoch 4/5\n3750/3750 [==============================] - 1s 194us/sample - loss: 2.2689 - acc: 0.2693\nEpoch 5/5\n3750/3750 [==============================] - 1s 188us/sample - loss: 2.2558 - acc: 0.3435\n","name":"stdout"},{"output_type":"execute_result","execution_count":93,"data":{"text/plain":""},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"# K Neighbors Classifier\nfor x in range (5):\n knn = KNeighborsClassifier(n_neighbors = (x + 1))\n knn.fit(X_train, y_train)\n preds_training = knn.predict(X_train)\n preds_testing = knn.predict(X_test)\n print(\"accuracy: \" + str(sum(preds_testing == y_test)/y_test.size))\n # k = 5 is the most accurate at 0.9224","execution_count":3,"outputs":[{"output_type":"stream","text":"accuracy: 0.9208\naccuracy: 0.9104\naccuracy: 0.9208\naccuracy: 0.9176\naccuracy: 0.9224\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Random Forest Classifier\nfor x in range(1, 51):\n model = RandomForestClassifier(n_estimators = x)\n model.fit(X_train, y_train)\n print(\"n_estimators: \" + str(x) + \" accuracy: \" + str(model.score(X_test, y_test)))\n #\n #41","execution_count":91,"outputs":[{"output_type":"stream","text":"n_estimators: 1 accuracy: 0.6464\nn_estimators: 2 accuracy: 0.6736\nn_estimators: 3 accuracy: 0.7632\nn_estimators: 4 accuracy: 0.7968\nn_estimators: 5 accuracy: 0.8208\nn_estimators: 6 accuracy: 0.8288\nn_estimators: 7 accuracy: 0.8552\nn_estimators: 8 accuracy: 0.864\nn_estimators: 9 accuracy: 0.868\nn_estimators: 10 accuracy: 0.8784\nn_estimators: 11 accuracy: 0.884\nn_estimators: 12 accuracy: 0.9072\nn_estimators: 13 accuracy: 0.8984\nn_estimators: 14 accuracy: 0.8864\nn_estimators: 15 accuracy: 0.8952\nn_estimators: 16 accuracy: 0.9048\nn_estimators: 17 accuracy: 0.8976\nn_estimators: 18 accuracy: 0.9112\nn_estimators: 19 accuracy: 0.9024\nn_estimators: 20 accuracy: 0.8992\nn_estimators: 21 accuracy: 0.9008\nn_estimators: 22 accuracy: 0.9048\nn_estimators: 23 accuracy: 0.9088\nn_estimators: 24 accuracy: 0.9024\nn_estimators: 25 accuracy: 0.9072\nn_estimators: 26 accuracy: 0.9112\nn_estimators: 27 accuracy: 0.9104\nn_estimators: 28 accuracy: 0.9168\nn_estimators: 29 accuracy: 0.9088\nn_estimators: 30 accuracy: 0.912\nn_estimators: 31 accuracy: 0.9216\nn_estimators: 32 accuracy: 0.9176\nn_estimators: 33 accuracy: 0.9144\nn_estimators: 34 accuracy: 0.9152\nn_estimators: 35 accuracy: 0.9136\nn_estimators: 36 accuracy: 0.9136\nn_estimators: 37 accuracy: 0.9152\nn_estimators: 38 accuracy: 0.912\nn_estimators: 39 accuracy: 0.92\nn_estimators: 40 accuracy: 0.9152\nn_estimators: 41 accuracy: 0.9224\nn_estimators: 42 accuracy: 0.9216\nn_estimators: 43 accuracy: 0.9216\nn_estimators: 44 accuracy: 0.916\nn_estimators: 45 accuracy: 0.9176\nn_estimators: 46 accuracy: 0.9192\nn_estimators: 47 accuracy: 0.9208\nn_estimators: 48 accuracy: 0.9176\nn_estimators: 49 accuracy: 0.9112\nn_estimators: 50 accuracy: 0.9144\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Optimal Random Forest Classifier\n#Fits this classifier to all of the data\nmodel = RandomForestClassifier(n_estimators = 41)\nmodel.fit(train.drop('label', axis = 1), train['label'])\n","execution_count":107,"outputs":[{"output_type":"execute_result","execution_count":107,"data":{"text/plain":"RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini',\n max_depth=None, max_features='auto', max_leaf_nodes=None,\n min_impurity_decrease=0.0, min_impurity_split=None,\n min_samples_leaf=1, min_samples_split=2,\n min_weight_fraction_leaf=0.0, n_estimators=41, n_jobs=None,\n oob_score=False, random_state=None, verbose=0,\n warm_start=False)"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"#print(pd.read_csv('../input/sample_submission.csv'))","execution_count":119,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"type(pd.read_csv('../input/sample_submission.csv'))","execution_count":97,"outputs":[{"output_type":"execute_result","execution_count":97,"data":{"text/plain":"pandas.core.frame.DataFrame"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"prediction = model.predict(test)\nd = {'ImageId' : range(1, 28001), 'Label': [0 for x in range(0, 28000)]}\nfor i in range(0, 28000):\n d['Label'][i] = prediction[i]# {'ImageId': i, 'Label': prediction[i]}\ndf = pd.DataFrame(data=d)\nprint(df)","execution_count":146,"outputs":[{"output_type":"stream","text":" ImageId Label\n0 1 2\n1 2 0\n2 3 9\n3 4 9\n4 5 3\n5 6 7\n6 7 0\n7 8 3\n8 9 0\n9 10 3\n10 11 5\n11 12 7\n12 13 4\n13 14 0\n14 15 4\n15 16 3\n16 17 3\n17 18 1\n18 19 9\n19 20 0\n20 21 9\n21 22 1\n22 23 1\n23 24 5\n24 25 7\n25 26 4\n26 27 2\n27 28 7\n28 29 9\n29 30 7\n... ... ...\n27970 27971 5\n27971 27972 0\n27972 27973 4\n27973 27974 8\n27974 27975 0\n27975 27976 3\n27976 27977 6\n27977 27978 0\n27978 27979 1\n27979 27980 9\n27980 27981 3\n27981 27982 1\n27982 27983 1\n27983 27984 0\n27984 27985 4\n27985 27986 5\n27986 27987 2\n27987 27988 2\n27988 27989 9\n27989 27990 6\n27990 27991 7\n27991 27992 6\n27992 27993 1\n27993 27994 9\n27994 27995 7\n27995 27996 9\n27996 27997 7\n27997 27998 3\n27998 27999 9\n27999 28000 2\n\n[28000 rows x 2 columns]\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"df.to_csv('submission.csv', index=False)","execution_count":155,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#print(pd.read_csv('../input/sample_submission.csv'))\n#df\n#pd.read_csv('../input/sample_submission.csv')\n#print(test)","execution_count":154,"outputs":[{"output_type":"execute_result","execution_count":154,"data":{"text/plain":" ImageId Label\n0 1 0\n1 2 0\n2 3 0\n3 4 0\n4 5 0\n5 6 0\n6 7 0\n7 8 0\n8 9 0\n9 10 0\n10 11 0\n11 12 0\n12 13 0\n13 14 0\n14 15 0\n15 16 0\n16 17 0\n17 18 0\n18 19 0\n19 20 0\n20 21 0\n21 22 0\n22 23 0\n23 24 0\n24 25 0\n25 26 0\n26 27 0\n27 28 0\n28 29 0\n29 30 0\n... ... ...\n27970 27971 0\n27971 27972 0\n27972 27973 0\n27973 27974 0\n27974 27975 0\n27975 27976 0\n27976 27977 0\n27977 27978 0\n27978 27979 0\n27979 27980 0\n27980 27981 0\n27981 27982 0\n27982 27983 0\n27983 27984 0\n27984 27985 0\n27985 27986 0\n27986 27987 0\n27987 27988 0\n27988 27989 0\n27989 27990 0\n27990 27991 0\n27991 27992 0\n27992 27993 0\n27993 27994 0\n27994 27995 0\n27995 27996 0\n27996 27997 0\n27997 27998 0\n27998 27999 0\n27999 28000 0\n\n[28000 rows x 2 columns]","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
ImageIdLabel
010
120
230
340
450
560
670
780
890
9100
10110
11120
12130
13140
14150
15160
16170
17180
18190
19200
20210
21220
22230
23240
24250
25260
26270
27280
28290
29300
.........
27970279710
27971279720
27972279730
27973279740
27974279750
27975279760
27976279770
27977279780
27978279790
27979279800
27980279810
27981279820
27982279830
27983279840
27984279850
27985279860
27986279870
27987279880
27988279890
27989279900
27990279910
27991279920
27992279930
27993279940
27994279950
27995279960
27996279970
27997279980
27998279990
27999280000
\n

28000 rows × 2 columns

\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}