{"cells":[{"metadata":{},"cell_type":"markdown","source":"Basic EDA for  Google Landmark Retrieval 2020. \nHelp taken from kernels\n\nhttps://www.kaggle.com/huangxiaoquan/google-landmarks-v2-exploratory-data-analysis-eda\nhttps://www.kaggle.com/seriousran/google-landmark-retrieval-2020-eda\n\nPlease upvote if you like","execution_count":null},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport seaborn as sns\nimport matplotlib.pyplot as plt\nfrom scipy import stats\nimport os\nimport glob\nimport cv2","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(os.listdir(\"../input\"))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_file_path = '../input/landmark-retrieval-2020/train.csv'","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train = pd.read_csv(train_file_path)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(\"Training data size:\", df_train.shape)\nprint(\"Training data columns:\",df_train.columns)\nprint(df_train.info())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train.head(3)\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Data Sample","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train.sample(3).sort_index()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Data tail","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train.tail(3)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Explore the specific element","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"select = [4444, 10000, 14005]\ndf_train.iloc[select,:]","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Check if the data is None","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"print('data is None.')\nmissing = df_train.isnull().sum()\npercent = missing/df_train.count()\nmissing_train_data = pd.concat([missing,percent],\n                              axis=1, keys=['Missing','Percent'])\nmissing_train_data.head()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Overall Basic Information","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train['landmark_id'].describe()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Object containing counts of unique values","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.set()\nprint(df_train.nunique())\ndf_train['landmark_id'].value_counts().hist()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Landmark_id distribuition","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.set()\nplt.title('Landmark_id Distribution')\nsns.distplot(df_train['landmark_id'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.set()\nplt.title('Training set: number of images per class(line plot)')\nsns.set_color_codes(\"pastel\")\nlandmarks_fold = pd.DataFrame(df_train['landmark_id'].value_counts())\nlandmarks_fold.reset_index(inplace=True)\nlandmarks_fold.columns = ['landmark_id','count']\nax = landmarks_fold['count'].plot(logy=True, grid=True)\nlocs,labels = plt.xticks()\nplt.setp(labels,rotation=30)\nax.set(xlabel=\"Landmarks\",ylabel=\"Number of images\")","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Training set: number of images per class(scatter plot)","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.set()\nlandmarks_fold_sorted = pd.DataFrame(df_train['landmark_id'].value_counts())\nlandmarks_fold_sorted.reset_index(inplace=True)\nlandmarks_fold_sorted.columns = ['landmark_id','count']\nlandmarks_fold_sorted = landmarks_fold_sorted.sort_values('landmark_id')\nax = landmarks_fold_sorted.plot.scatter(\\\n     x='landmark_id',y='count',\n     title='Training set: number of images per class(statter plot)')\nlocs, labels = plt.xticks()\nplt.setp(labels, rotation=30)\nax.set(xlabel=\"Landmarks\", ylabel=\"Number of images\")","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Visualize outliers, min/max or quantiles of the landmarks count\n","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.set()\nax = landmarks_fold_sorted.boxplot(column='count')\nax.set_yscale('log')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.set()\nres = stats.probplot(df_train['landmark_id'], plot=plt)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Specific Basic Information","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"threshold = [2, 3, 5, 10, 20, 50, 100]\nfor num in threshold:    \n    print(\"Number of classes under {}: {}/{} \"\n          .format(num, (df_train['landmark_id'].value_counts() < num).sum(), \n                  len(df_train['landmark_id'].unique()))\n          )","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Most frequent landmark_ids","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"temp = pd.DataFrame(df_train.landmark_id.value_counts().head(10))\ntemp.reset_index(inplace=True)\ntemp.columns = ['landmark_id', 'count']\ntemp","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.set()\nplt.title('Most frequent landmarks')\nsns.set_color_codes(\"pastel\")\nsns.barplot(x=\"landmark_id\", y=\"count\", data=temp,\n           label=\"count\")\nlocs, labels = plt.xticks()\nplt.setp(labels, rotation=45)\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Least frequent landmark_ids","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"temp = pd.DataFrame(df_train.landmark_id.value_counts().tail(10))\ntemp.reset_index(inplace=True)\ntemp.columns = ['landmark_id', 'count']\ntemp","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.set()\n# plt.figure(figsize=(9, 8))\nplt.title('Least frequent landmarks')\nsns.set_color_codes(\"pastel\")\nsns.barplot(x=\"landmark_id\", y=\"count\", data=temp,\n            label=\"Count\")\nlocs, labels = plt.xticks()\nplt.setp(labels, rotation=45)\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Test and index data**\n\n\nThe query images are listed in the test/ folder, while the \"index\" images from which you are retrieving are listed in index/.\n\nEach image has a unique id. Since there are a large number of images, each image is placed within three subfolders according to the first three characters of the image id (i.e. image abcdef.jpg is placed in a/b/c/abcdef.jpg).\n\n0-f in 0-f in 0-f","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"test_list = glob.glob('../input/landmark-retrieval-2020/test/*/*/*/*')\nindex_list = glob.glob('../input/landmark-retrieval-2020/index/*/*/*/*')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Display examples\n","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.rcParams[\"axes.grid\"] = False\nf, axarr = plt.subplots(4, 3, figsize=(24, 22))\n\ncurr_row = 0\nfor i in range(12):\n    example = cv2.imread(test_list[i])\n    example = example[:,:,::-1]\n    \n    col = i%4\n    axarr[col, curr_row].imshow(example)\n    if col == 3:\n        curr_row += 1\n","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}