{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport seaborn as sns\nfrom pathlib import Path\nfrom PIL import Image\n\nimport plotly.graph_objects as go\nimport matplotlib.pyplot as plt","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"%ls ../input/bengaliai-cv19/","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"dataset_path = Path(\"../input/bengaliai-cv19\")\nnum_dataset_count = 4\ntrain_path = dataset_path / \"train.csv\"\ntest_path = dataset_path / \"test.csv\"\nclass_map_path = dataset_path / \"class_map.csv \"\nsample_submit_path = dataset_path / \"sample_submission.csv\"\n\next = \".parquet\"\ntrain_prefix = \"train_image_data_\"\ntest_prefix = \"test_image_data_\"\ntrain_image_paths = []\ntest_image_paths = []\nfor idx in range(num_dataset_count):\n    train_image_path = \"{}{}{}\".format(train_prefix, idx, ext)\n    train_image_paths.append(train_image_path)\n    test_image_path = \"{}{}{}\".format(test_prefix, idx, ext)\n    test_image_paths.append(test_image_path)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train = pd.read_csv(train_path)\ntest = pd.read_csv(test_path)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.shape, test.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"first_target_col = \"grapheme_root\"\nsecond_target_col = \"vowel_diacritic\"\nthird_target_col = \"consonant_diacritic\"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fig = go.Figure(data=[go.Histogram(x=train[first_target_col])])\nfig.update_layout(title_text='{} value_counts'.format(first_target_col))\nfig.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fig = go.Figure(data=[go.Histogram(x=train[second_target_col])])\nfig.update_layout(title_text='{} value_counts'.format(second_target_col))\nfig.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fig = go.Figure(data=[go.Histogram(x=train[third_target_col])])\nfig.update_layout(title_text='{} value_counts'.format(third_target_col))\nfig.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"label_train = train.drop(columns=[\"image_id\", \"grapheme\"])\nlabel_train[label_train.duplicated()].shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_combs = train.groupby([first_target_col, second_target_col, third_target_col]).size().reset_index().rename(columns={0:'count'})","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fig = go.Figure(data=[go.Bar(x=train_combs.index, y=train_combs[\"count\"])])\nfig.update_layout(title_text='unique combination value_counts')\nfig.show()","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}