{"cells":[{"metadata":{},"cell_type":"markdown","source":"# Digit Recogniser"},{"metadata":{},"cell_type":"markdown","source":"## Imports"},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nfrom matplotlib import pyplot as plt\nimport seaborn as sns\nplt.style.use('seaborn')\nimport os","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Data"},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"for dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Load data**"},{"metadata":{"trusted":true},"cell_type":"code","source":"train = pd.read_csv('/kaggle/input/digit-recognizer/train.csv')\ntest = pd.read_csv('/kaggle/input/digit-recognizer/test.csv')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Number of train samples by label**"},{"metadata":{"trusted":true},"cell_type":"code","source":"train.label.value_counts().plot.bar(rot=0,title='Number of train samples by label');","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Random Sample to Image**"},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.imshow(train[train.columns[1:]].sample(1).values.ravel().reshape(28,28));","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Train / Test data**"},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import train_test_split","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_, test_ = train_test_split(train,test_size=0.33,random_state=42,stratify=train.label)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Check if the data it's fair splitted based on label**"},{"metadata":{"trusted":true},"cell_type":"code","source":"'train',train_.label.value_counts() / len(train_),'test',test_.label.value_counts() / len(test_)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**KNN**"},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.neighbors import KNeighborsClassifier\nfrom sklearn import metrics","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\nknn = KNeighborsClassifier(n_neighbors=3)\nknn.fit(train_[train_.columns[1:]],train_['label'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\nknn_results = test_.copy()\nknn_results['y_pred'] = knn.predict(test_[test_.columns[1:]])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(metrics.classification_report(knn_results.label,knn_results.y_pred))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.heatmap(metrics.confusion_matrix(knn_results.label,knn_results.y_pred),annot=True,fmt='d');","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**XGBoost**"},{"metadata":{"trusted":true},"cell_type":"code","source":"import xgboost as xgb","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\nxgc = xgb.XGBClassifier(objective='multi:softmax',num_class=train.label.nunique(),n_estimators=300)\nxgc.fit(train_[train_.columns[1:]],train_['label'],verbose=1000)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\nxgc_results = test_.copy()\nxgc_results['y_pred'] = xgc.predict(test_[test_.columns[1:]])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(metrics.classification_report(xgc_results.label,xgc_results.y_pred))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.heatmap(metrics.confusion_matrix(xgc_results.label,xgc_results.y_pred),annot=True,fmt='d');","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Train on Full Data then create submission file**"},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\nfull_xgc = xgb.XGBClassifier(objective='multi:softmax',num_class=train.label.nunique(),n_estimators=300)\nfull_xgc.fit(train[train.columns[1:]],train['label'],verbose=1000)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\nfull_xgc_results = test.copy()\nfull_xgc_results['y_pred'] = full_xgc.predict(test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"full_xgc_results['ImageId'] = list(range(1,len(test) + 1))\nfull_xgc_results[['ImageId','y_pred']].rename(columns={'y_pred':'label'}).to_csv('submission.csv',index=False)","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}