{"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\nfrom matplotlib.gridspec import  GridSpec\nimport seaborn as sns\n# Input data files are available in the \"../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# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train_df = pd.read_csv('../input/bengaliai-cv19/train.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df.tail()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_df = pd.read_csv('../input/bengaliai-cv19/test.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_df.tail()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_image_0 = pd.read_parquet('/kaggle/input/bengaliai-cv19/train_image_data_0.parquet')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_image_0.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"IMAGE_ROW = 137 \nIMAGE_COLUMN = 236\n\ntrain_image0 = train_image_0.drop('image_id', axis =1)\n\ndef display_image(idx): \n    img = train_image0[idx:idx+1].values[0].reshape([IMAGE_ROW, IMAGE_COLUMN])\n    plt.imshow(img, cmap = 'gray')\n    plt.axis('off')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_image0[1:2].values[0]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"display_image(70)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def display_range_images(idx): \n    gr, vd, cd = list(train_df.iloc[idx][['grapheme_root', 'vowel_diacritic', 'consonant_diacritic']])\n    figure, ax = plt.subplots(3,3)\n    figure.tight_layout(rect=[0, 0.03, 1, 0.90])\n    same_char_loc = list(train_df[(train_df['grapheme_root'] == gr) & \n                        (train_df['vowel_diacritic'] == vd) & \n                        (train_df['consonant_diacritic'] == cd)].index)[:9]\n    for i in range(9):\n        plt.subplot(3,3,i+1)\n        plt.axis('off')\n        cidx = same_char_loc[i]\n        img = train_image0[cidx:cidx+1].values[0].reshape([IMAGE_ROW, IMAGE_COLUMN])\n        plt.imshow(img, cmap = 'gray')\n    figure.suptitle('Grapheme Root Class: {} \\n Vowel Diacritic Class: {} \\n Consonant Diacritic Class: {}'.format(gr,vd,cd))\n    plt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"display_range_images(10)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"list(train_df.iloc[70][['grapheme_root', 'vowel_diacritic', 'consonant_diacritic']])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\"\"\"\ngrapheme_root               148\nvowel_diacritic               0\nconsonant_diacritic           5\n\"\"\"\ntrain_df[(train_df['grapheme_root'] == 115) & \n         (train_df['vowel_diacritic'] == 1) & \n         (train_df['consonant_diacritic'] == 0)].index[:9]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"no_cs = train_df[(train_df['grapheme_root'] == 115) & \n         (train_df['vowel_diacritic'] == 1) & \n         (train_df['consonant_diacritic'] == 0)].index[:2]\nwith_cs = train_df[(train_df['grapheme_root'] == 115) & \n         (train_df['vowel_diacritic'] == 1) & \n         (train_df['consonant_diacritic'] == 2)].index[:2]\nfig, ax = plt.subplots(2,2)\nfig.suptitle('Grapheme Root Class: 115 \\n Vowel Diacritic Class: 1')\nfig.tight_layout(rect=[0, 0.03, 1, 0.85])\nfor i in range(4):\n    plt.subplot(2,2,i+1)\n    plt.axis('off')\n    if i % 2 == 0:\n        idx = no_cs[i // 2]\n        print(idx)\n        img = train_image0[idx:idx+1].values[0].reshape([IMAGE_ROW, IMAGE_COLUMN])\n        if i == 0:\n            plt.title('Consonant Diacritic: 0')\n        plt.imshow(img, cmap = 'gray')\n    else:\n        idx = with_cs[i // 2]\n        print(idx)\n        img = train_image0[idx:idx+1].values[0].reshape([IMAGE_ROW, IMAGE_COLUMN])\n        if i == 1:\n            plt.title('Consonant Diacritic: 2')\n        plt.imshow(img, cmap = 'gray')\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"roots = train_df.groupby(by=['grapheme_root']).count()\nroots = roots.reset_index()[['grapheme_root', 'image_id']].sort_values(by=['image_id'], ascending = False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"roots['count'] = roots['image_id']\nroots = roots.drop('image_id', axis = 1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fig,ax = plt.subplots(figsize=(15,5))\nsns.barplot(x = 'grapheme_root', y='count', data = roots, order=roots['grapheme_root'])\nplt.xticks(rotation=90)\nfig.tight_layout()\nplt.title('Number of images in the Training set across Grapheme Root classes', fontsize = 18)\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"vowels = train_df.groupby(by=['vowel_diacritic']).count()\nvowels = vowels.reset_index()[['vowel_diacritic', 'image_id']].sort_values(by=['image_id'], ascending = False)\nvowels['count'] = vowels['image_id']\nvowels = vowels.drop('image_id', axis = 1)\n\nconsonants = train_df.groupby(by=['consonant_diacritic']).count()\nconsonants = consonants.reset_index()[['consonant_diacritic', 'image_id']].sort_values(by=['image_id'], ascending = False)\nconsonants['count'] = consonants['image_id']\nconsonants = consonants.drop('image_id', axis = 1)\nfigure,ax = plt.subplots(1,2,figsize = (8,4))\nplt.subplot(121)\nsns.barplot(x = 'vowel_diacritic', y='count', data = vowels, order=vowels['vowel_diacritic'])\nplt.title('Number of images per Vowel Diacritic', fontsize = 12)\nplt.subplot(122)\nsns.barplot(x = 'consonant_diacritic', y='count', data = consonants, order=consonants['consonant_diacritic'])\nplt.title('Number of images per Consonant Diacritic', fontsize = 12)\nplt.tight_layout()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"vowels","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":1}