{"cells":[{"metadata":{"trusted":true},"cell_type":"code","source":"import plotly.express as px\nfrom plotly.subplots import make_subplots\nimport plotly.graph_objs as go\n","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"collapsed":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\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../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# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Training Data\n\nThe main file that serves as an index of all training data is train.csv.\nThis file has two columns, *segment_id* and *time_to_eruption*.\nEach segment_id points to another training data csv file.\nThe time_to_eruption is what we want to predict."},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train_index = pd.read_csv('/kaggle/input/predict-volcanic-eruptions-ingv-oe/train.csv')\nprint(f\"Columns in train.csv: {list(train_index.columns)}\")\nprint(f\"Number of segments in training: {len(train_index)}\")\nprint(\"*\" * 60)\nprint(\"Training Index Data:\")\nprint(train_index.head())","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Time to Eruption\n\nThe distribution of time_to_eruption of all training data."},{"metadata":{"trusted":true},"cell_type":"code","source":"%matplotlib inline\ntrain_index['time_to_eruption'].hist(bins=100)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Training Data\n\nLet's read training data for one segment_id:"},{"metadata":{"trusted":true},"cell_type":"code","source":"df = pd.read_csv('/kaggle/input/predict-volcanic-eruptions-ingv-oe/train/900763028.csv')\nprint(f\"Number of rows for segment_id 900763028 in train: {len(df)}\")\nprint(f\"Number of columns (features): {len(df.columns)}\")\nprint(f\"List of available features: {list(df.columns)}\")\nprint(\"*\" * 60)\nprint(\"Training Data for segment_id: 900763028\")\nprint(df.head())","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# # Combine the training data "},{"metadata":{"trusted":true},"cell_type":"code","source":"test = pd.read_csv('/kaggle/input/predict-volcanic-eruptions-ingv-oe/test/1282708307.csv')\nprint(len(test))\ntest.head()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Submission File\n\nSample Submission File:"},{"metadata":{"trusted":true},"cell_type":"code","source":"ss = pd.read_csv(\"/kaggle/input/predict-volcanic-eruptions-ingv-oe/sample_submission.csv\")\nss","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}