{"cells":[{"metadata":{},"cell_type":"markdown","source":"**Load Packages-**"},{"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\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":{},"cell_type":"markdown","source":"**DATA EXPLORATION-**"},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_submission = pd.read_csv('/kaggle/input/bengaliai-cv19/sample_submission.csv')\nsample_submission.head()","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('/kaggle/input/bengaliai-cv19/train.csv')\ntrain_df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(f\"\"\"there are {train_df['grapheme_root'].nunique()} grapheme_root, {train_df['vowel_diacritic'].nunique()} vowel_diacritics and {train_df['consonant_diacritic'].nunique()} consonant_diacritic.\"\"\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(f\"\"\"Most frequent graphene_root is {train_df['grapheme_root'].value_counts().index[0]}\nMost frequent vowel_diacritic is {train_df['vowel_diacritic'].value_counts().index[0]}\nMost frequent consonant_diacritic is {train_df['consonant_diacritic'].value_counts().index[0]}\"\"\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plots=train_df[\"grapheme_root\"].value_counts().reset_index()\nplots.columns = ['grapheme_root', 'counts']\nplt.scatter( x=plots.grapheme_root, y=plots.counts, c='g', s= (plots.counts/20))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"class_map_df = pd.read_csv('/kaggle/input/bengaliai-cv19/class_map.csv')\nclass_map_df.tail()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"class_map_df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"class_map_df.shape","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Exploring Parquet Files-**\nParquet files are best suited for Apache Hadoop system and good for storing files as pixels are arranged in columar pattern."},{"metadata":{"trusted":true},"cell_type":"code","source":"img = pd.read_parquet('/kaggle/input/bengaliai-cv19/train_image_data_1.parquet')\nimg.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"img.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"img_id = img.iloc[:,0]\nimage = img.iloc[:,1:].values.reshape(-1, 137,236)\nimage","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Getting Images from data-**"},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.figure(figsize=(12,12))\nfor i in range(10):\n plt.subplot(5,5,i+1)\n plt.imshow(image[i])","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}