{"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_minor":4,"nbformat":4,"cells":[{"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","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2021-12-23T14:53:28.156349Z","iopub.execute_input":"2021-12-23T14:53:28.156718Z","iopub.status.idle":"2021-12-23T14:53:28.191463Z","shell.execute_reply.started":"2021-12-23T14:53:28.156611Z","shell.execute_reply":"2021-12-23T14:53:28.190714Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!pip install plotly","metadata":{"execution":{"iopub.status.busy":"2021-12-23T14:53:29.147912Z","iopub.execute_input":"2021-12-23T14:53:29.148419Z","iopub.status.idle":"2021-12-23T14:53:40.027752Z","shell.execute_reply.started":"2021-12-23T14:53:29.148382Z","shell.execute_reply":"2021-12-23T14:53:40.026731Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# G-Research Crypto Forecasting\n\nCryptocurrencies are very popular but have the disavantage to be more volatile than classical stock prices. The first cryptocurrency, Bitcoin, was created in 2008 by Satoshi Nakamoto. Bitcoin is created as a decentralized system based on the blockchain technology. However, in the next years, creation of many other cryptocurrencies has been exploded. The expansion and democratization of these methods have opened new horizons for stock market.\n\n\nIn this Kaggle competition, the aim is to predict trends about cryptocurrencies by using the most well-knowledge currencies. It is important to keep in mind that forecasting stock market is a hard task and thus, forecasting trends in cryptocurrencies is harder.\n\n\n# Datasets\n\n\nIn this competition, 5 files are available :\n\n\nA first train set,\n\nA supplementary train set,\n\nAn asset set with information about cryptocurrencies,\n\nAn example test,\n\nAn example test submission.\n\nOnly three datasets (the two train sets & the asset set) were used in this exploration.\n\n\nConfiguration and Utils","metadata":{}},{"cell_type":"code","source":"# system libraries\nimport warnings\nwarnings.filterwarnings('ignore')\nwarnings.simplefilter(action='ignore', category=FutureWarning)\nimport logging\nlogging.disable(logging.CRITICAL)\nimport gc\n\n# graphical libraries\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nimport plotly.express as px\nimport plotly.graph_objects as go\nfrom plotly.subplots import make_subplots\n\nfrom functools import reduce\nfrom datetime import datetime\nimport time","metadata":{"execution":{"iopub.status.busy":"2021-12-23T14:54:54.074235Z","iopub.execute_input":"2021-12-23T14:54:54.074531Z","iopub.status.idle":"2021-12-23T14:54:56.555189Z","shell.execute_reply.started":"2021-12-23T14:54:54.074489Z","shell.execute_reply":"2021-12-23T14:54:56.554192Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"dtype_dict ={\"open\" : \"float16\",\n             \"close\" : \"float16\",\n             \"high\" : \"float16\",\n             \"low\" : \"float16\",\n             \"volume\" : \"float16\",\n             \"vwap\" : \"float16\",\n             \"target\" : \"float16\"}","metadata":{"execution":{"iopub.status.busy":"2021-12-23T14:55:02.604750Z","iopub.execute_input":"2021-12-23T14:55:02.605065Z","iopub.status.idle":"2021-12-23T14:55:02.610174Z","shell.execute_reply.started":"2021-12-23T14:55:02.605009Z","shell.execute_reply":"2021-12-23T14:55:02.609183Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def crypto_df(asset_id, data):\n    # Copied from https://www.kaggle.com/odins0n/g-research-plots-eda\n    df = data[data[\"asset_name\"] == asset_id].reset_index(drop=True)\n    df['timestamp'] = pd.to_datetime(df['timestamp'], unit='s')\n    df = df.set_index('timestamp')\n    return df\n\n\ndef candelstick_chart(data, title):\n    # Copied from https://www.kaggle.com/odins0n/g-research-plots-eda\n    candlestick = go.Figure(data=[go.Candlestick(x=data.index,\n                                                 open=data[('open')],\n                                                 high=data[('high')],\n                                                 low=data[('low')],\n                                                 close=data[('close')])])\n    candlestick.update_xaxes(title_text='Time',\n                             rangeslider_visible=False)\n\n    candlestick.update_layout(\n        title={\n            'text': '{:} Candelstick Chart'.format(title),\n            'y': 0.90,\n            'x': 0.5,\n            'xanchor': 'center',\n            'yanchor': 'top'})\n\n    candlestick.update_yaxes(title_text='Price in USD', ticksuffix='$')\n    return candlestick\n\n\ndef vol_traded(data, title, color):\n    # Copied from https://www.kaggle.com/odins0n/g-research-plots-eda\n    area = px.area(data_frame=data,\n                   x=data.index,\n                   y=\"volume\")\n    area.update_traces(line_color=color)\n    area.update_xaxes(\n        title_text='Time',\n        rangeslider_visible=False)\n    area.update_yaxes(title_text='Number of trades every minute')\n    area.update_layout(showlegend=True,\n                       title={\n                           'text': '{:} Volume Traded'.format(title),\n                           'y': 0.94,\n                           'x': 0.5,\n                           'xanchor': 'center',\n                           'yanchor': 'top'})\n    return area","metadata":{"execution":{"iopub.status.busy":"2021-12-23T14:55:15.822001Z","iopub.execute_input":"2021-12-23T14:55:15.822320Z","iopub.status.idle":"2021-12-23T14:55:15.834754Z","shell.execute_reply.started":"2021-12-23T14:55:15.822287Z","shell.execute_reply":"2021-12-23T14:55:15.833233Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 1) Preprocessing","metadata":{}},{"cell_type":"code","source":"# Importing datasets\n\ndf = pd.read_csv(\"../input/g-research-crypto-forecasting/train.csv\", dtype=dtype_dict)\ndf_sup = pd.read_csv(\"../input/g-research-crypto-forecasting/supplemental_train.csv\", dtype=dtype_dict)\nasset = pd.read_csv(\"../input/g-research-crypto-forecasting/asset_details.csv\")\ndf.head()","metadata":{"execution":{"iopub.status.busy":"2021-12-23T14:55:36.141027Z","iopub.execute_input":"2021-12-23T14:55:36.141346Z","iopub.status.idle":"2021-12-23T14:56:39.729158Z","shell.execute_reply.started":"2021-12-23T14:55:36.141312Z","shell.execute_reply":"2021-12-23T14:56:39.728204Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df.shape","metadata":{"execution":{"iopub.status.busy":"2021-12-23T14:56:39.730626Z","iopub.execute_input":"2021-12-23T14:56:39.730877Z","iopub.status.idle":"2021-12-23T14:56:39.738353Z","shell.execute_reply.started":"2021-12-23T14:56:39.730845Z","shell.execute_reply":"2021-12-23T14:56:39.737289Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Columns of the dataset :\n\n\n* timestamp - A timestamp for the minute covered by the row.\n* Asset_ID - An ID code for the cryptoasset.\n* Count - The number of trades that took place this minute.\n* Open - The USD price at the beginning of the minute.\n* High - The highest USD price during the minute.\n* Low - The lowest USD price during the minute.\n* Close - The USD price at the end of the minute.\n* Volume - The number of cryptoasset units traded during the minute.\n* VWAP - The volume weighted average price for the minute.\n* Target - 15 minute residualized returns.","metadata":{}},{"cell_type":"code","source":"# Creating an unique df with data\ndf = df.append(df_sup,\n               ignore_index=True,\n               verify_integrity=True)","metadata":{"execution":{"iopub.status.busy":"2021-12-23T14:58:09.077953Z","iopub.execute_input":"2021-12-23T14:58:09.078292Z","iopub.status.idle":"2021-12-23T14:58:09.889372Z","shell.execute_reply.started":"2021-12-23T14:58:09.078259Z","shell.execute_reply":"2021-12-23T14:58:09.888368Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df.shape","metadata":{"execution":{"iopub.status.busy":"2021-12-23T14:58:15.114003Z","iopub.execute_input":"2021-12-23T14:58:15.114416Z","iopub.status.idle":"2021-12-23T14:58:15.120343Z","shell.execute_reply.started":"2021-12-23T14:58:15.114372Z","shell.execute_reply":"2021-12-23T14:58:15.119331Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Merging dataset to obtain name of each cryptocurrency\ndf = pd.merge(df, asset, on=\"Asset_ID\")\ndf = df[[\"timestamp\", \"Asset_Name\", \"Count\",\n         \"Open\", \"High\", \"Low\",\n         \"Close\", \"Volume\", \"VWAP\",\n         \"Target\"]]\ndf.columns = [\"timestamp\", \"asset_name\", \"count\",\n              \"open\", \"high\", \"low\",\n              \"close\", \"volume\", \"vwap\",\n              \"target\"]\ndf.head()","metadata":{"execution":{"iopub.status.busy":"2021-12-23T14:58:52.655385Z","iopub.execute_input":"2021-12-23T14:58:52.655704Z","iopub.status.idle":"2021-12-23T14:59:00.592917Z","shell.execute_reply.started":"2021-12-23T14:58:52.655670Z","shell.execute_reply":"2021-12-23T14:59:00.592063Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Missing values exploration\ndf.isnull().mean() * 100","metadata":{"execution":{"iopub.status.busy":"2021-12-23T14:59:02.151015Z","iopub.execute_input":"2021-12-23T14:59:02.151312Z","iopub.status.idle":"2021-12-23T14:59:04.966203Z","shell.execute_reply.started":"2021-12-23T14:59:02.151280Z","shell.execute_reply":"2021-12-23T14:59:04.965228Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Deleting missing data\ndf.dropna(inplace=True)","metadata":{"execution":{"iopub.status.busy":"2021-12-23T14:59:16.266693Z","iopub.execute_input":"2021-12-23T14:59:16.266966Z","iopub.status.idle":"2021-12-23T14:59:21.318629Z","shell.execute_reply.started":"2021-12-23T14:59:16.266935Z","shell.execute_reply":"2021-12-23T14:59:21.317578Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 2) Exploratory Analysis\n\na) Candlestick representation\n\nIn this part, data will be visualised with the help of candlestick graphs. This kind of graph is used to see information about open, close, high and low values of a currency during a certain period of time. Here, the last 120 minutes were reprensented. To realize the graph, a dataframe for each currency was created. Then, Plotly library was used to displayed the graphs","metadata":{}},{"cell_type":"code","source":"btc = crypto_df(\"Bitcoin\", data=df)\neth = crypto_df(\"Ethereum\", data=df)\niota = crypto_df(\"IOTA\", data=df)","metadata":{"execution":{"iopub.status.busy":"2021-12-23T14:59:46.251942Z","iopub.execute_input":"2021-12-23T14:59:46.252550Z","iopub.status.idle":"2021-12-23T14:59:56.369853Z","shell.execute_reply.started":"2021-12-23T14:59:46.252505Z","shell.execute_reply":"2021-12-23T14:59:56.369111Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"btc_plot = candelstick_chart(btc[-120:], title=\"Bitcoin\")\nbtc_plot.show()","metadata":{"execution":{"iopub.status.busy":"2021-12-23T15:02:39.563623Z","iopub.execute_input":"2021-12-23T15:02:39.565035Z","iopub.status.idle":"2021-12-23T15:02:39.754211Z","shell.execute_reply.started":"2021-12-23T15:02:39.564964Z","shell.execute_reply":"2021-12-23T15:02:39.753275Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"eth_plot = candelstick_chart(eth[-120:], title=\"Ethereum\")\neth_plot.show()","metadata":{"execution":{"iopub.status.busy":"2021-12-23T15:06:25.980801Z","iopub.execute_input":"2021-12-23T15:06:25.981332Z","iopub.status.idle":"2021-12-23T15:06:26.014063Z","shell.execute_reply.started":"2021-12-23T15:06:25.981289Z","shell.execute_reply":"2021-12-23T15:06:26.013099Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"iota_plot = candelstick_chart(iota[-120:], title=\"IOTA\")\niota_plot.show()","metadata":{"execution":{"iopub.status.busy":"2021-12-23T15:06:34.177871Z","iopub.execute_input":"2021-12-23T15:06:34.178295Z","iopub.status.idle":"2021-12-23T15:06:34.203788Z","shell.execute_reply.started":"2021-12-23T15:06:34.178162Z","shell.execute_reply":"2021-12-23T15:06:34.202882Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Visually, we can conclude that some currencies are more stable than others. The ups and downs seems to follow the same series but the amplitude are variable. For instance, IOTA shows great difference between the parameters ohlc.\n\n\nb) Volume exchange\n\nSecond visualisation is about volume traded during the last 60 minutes.\n\n\nBitcoin","metadata":{}},{"cell_type":"code","source":"vol_traded(btc[-60:], \"Bitcoin\", color=\"Blue\")","metadata":{"execution":{"iopub.status.busy":"2021-12-23T15:15:49.847736Z","iopub.execute_input":"2021-12-23T15:15:49.848144Z","iopub.status.idle":"2021-12-23T15:15:51.101871Z","shell.execute_reply.started":"2021-12-23T15:15:49.848101Z","shell.execute_reply":"2021-12-23T15:15:51.101032Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"vol_traded(eth[-60:], \"Ethereum\", color=\"Green\")","metadata":{"execution":{"iopub.status.busy":"2021-12-23T15:16:41.540424Z","iopub.execute_input":"2021-12-23T15:16:41.540771Z","iopub.status.idle":"2021-12-23T15:16:41.623268Z","shell.execute_reply.started":"2021-12-23T15:16:41.540727Z","shell.execute_reply":"2021-12-23T15:16:41.622477Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"vol_traded(iota[-60:], \"IOTA\", color=\"Green\")","metadata":{"execution":{"iopub.status.busy":"2021-12-23T15:16:50.384990Z","iopub.execute_input":"2021-12-23T15:16:50.385897Z","iopub.status.idle":"2021-12-23T15:16:50.464885Z","shell.execute_reply.started":"2021-12-23T15:16:50.385854Z","shell.execute_reply":"2021-12-23T15:16:50.463990Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"c) Central tendency analysis","metadata":{}},{"cell_type":"code","source":"df.groupby(\"asset_name\").mean()","metadata":{"execution":{"iopub.status.busy":"2021-12-23T15:17:14.785455Z","iopub.execute_input":"2021-12-23T15:17:14.785764Z","iopub.status.idle":"2021-12-23T15:17:19.431080Z","shell.execute_reply.started":"2021-12-23T15:17:14.785723Z","shell.execute_reply":"2021-12-23T15:17:19.429950Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df.groupby(\"asset_name\").median()","metadata":{"execution":{"iopub.status.busy":"2021-12-23T15:17:20.936169Z","iopub.execute_input":"2021-12-23T15:17:20.936675Z","iopub.status.idle":"2021-12-23T15:17:26.861027Z","shell.execute_reply.started":"2021-12-23T15:17:20.936640Z","shell.execute_reply":"2021-12-23T15:17:26.860146Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df.groupby(\"asset_name\").std()","metadata":{"execution":{"iopub.status.busy":"2021-12-23T15:17:28.126604Z","iopub.execute_input":"2021-12-23T15:17:28.126894Z","iopub.status.idle":"2021-12-23T15:17:33.520654Z","shell.execute_reply.started":"2021-12-23T15:17:28.126862Z","shell.execute_reply":"2021-12-23T15:17:33.519590Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"d) Correlation between cryptocurrencies","metadata":{}},{"cell_type":"code","source":"df_close = df.copy()\ndf_close = df_close[[\"timestamp\", \"asset_name\", \"close\"]]\ndf_close[\"timestamp\"] = df_close[\"timestamp\"].apply(\n    lambda x: datetime.fromtimestamp(x))\ndf_close[\"date\"] = df_close[\"timestamp\"].astype('datetime64[s]')\ndf_close.set_index(\"date\", inplace=True)\ndf_close.drop(\"timestamp\", axis=1, inplace=True)\ndf_close = df_close[[\"asset_name\", \"close\"]]\ndf_close[\"close\"] = df_close[\"close\"].apply(lambda x: np.log(x))","metadata":{"execution":{"iopub.status.busy":"2021-12-23T15:17:50.696757Z","iopub.execute_input":"2021-12-23T15:17:50.697089Z","iopub.status.idle":"2021-12-23T15:19:16.738023Z","shell.execute_reply.started":"2021-12-23T15:17:50.697052Z","shell.execute_reply":"2021-12-23T15:19:16.737250Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_close_2021 = df_close.loc['01/01/2021':'01/06/2021']\ndf_close_2021.reset_index(inplace=True)\ndf_close_2021 = pd.pivot_table(\n    df_close_2021, values=\"close\", columns=\"asset_name\", index=\"date\")","metadata":{"execution":{"iopub.status.busy":"2021-12-23T15:19:16.739690Z","iopub.execute_input":"2021-12-23T15:19:16.740453Z","iopub.status.idle":"2021-12-23T15:19:20.372808Z","shell.execute_reply.started":"2021-12-23T15:19:16.740421Z","shell.execute_reply":"2021-12-23T15:19:20.371976Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plt.figure(figsize=(15, 15))\nsns.heatmap(df_close_2021.diff().corr(),\n            linewidths=.5,\n            annot=True,\n            square=True,\n            cmap=\"viridis\")\nplt.xlabel(\"Asset Name\")\nplt.ylabel(\"Asset Name\")\nplt.title(\"Correlation matrix between each cryptocurrency during the first semester (2021)\")\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2021-12-23T15:19:20.374395Z","iopub.execute_input":"2021-12-23T15:19:20.375295Z","iopub.status.idle":"2021-12-23T15:19:21.773132Z","shell.execute_reply.started":"2021-12-23T15:19:20.375238Z","shell.execute_reply":"2021-12-23T15:19:21.772087Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"del df_close\ndel df_close_2021\ngc.collect()","metadata":{"execution":{"iopub.status.busy":"2021-12-23T15:19:21.775447Z","iopub.execute_input":"2021-12-23T15:19:21.775758Z","iopub.status.idle":"2021-12-23T15:19:22.027199Z","shell.execute_reply.started":"2021-12-23T15:19:21.775715Z","shell.execute_reply":"2021-12-23T15:19:22.026239Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 3) Features Engineering","metadata":{}},{"cell_type":"code","source":"dataset = [btc, eth, iota]\n\n\ncols = ['open', 'close', \"high\", \"low\"]\n\nfor i in dataset:\n    for j in cols:\n        i[\"log_\"+j] = i[j].apply(lambda x: np.log(x))","metadata":{"execution":{"iopub.status.busy":"2021-12-23T15:24:41.034253Z","iopub.execute_input":"2021-12-23T15:24:41.034654Z","iopub.status.idle":"2021-12-23T15:25:27.187311Z","shell.execute_reply.started":"2021-12-23T15:24:41.034617Z","shell.execute_reply":"2021-12-23T15:25:27.186235Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"* Stock High minus Low price (H-L)\n* Stock Close minus Open price (O-C)\n* Stock price’s seven days’ moving average (7 DAYS MA)\n* Stock price’s fourteen days’ moving average (14 DAYS MA)\n* Stock price’s twenty one days’ moving average (21 DAYS MA)\n* Stock price’s standard deviation for the past seven days (7 DAYS STD DEV)","metadata":{}},{"cell_type":"code","source":"for i in dataset:\n    i[\"H-L\"] = i[\"log_high\"] - i[\"log_low\"]\n    i[\"O-C\"] = i[\"log_open\"] - i[\"log_close\"]\n    i[\"MA_7d\"] = i[\"log_close\"].rolling(10080).mean()\n    i[\"MA_14d\"] = i[\"log_close\"].rolling(20160).mean()\n    i[\"MA_21d\"] = i[\"log_close\"].rolling(30240).mean()\n    i[\"STD_7d\"] = i[\"log_close\"].rolling(10080).std()","metadata":{"execution":{"iopub.status.busy":"2021-12-23T15:25:27.189649Z","iopub.execute_input":"2021-12-23T15:25:27.190014Z","iopub.status.idle":"2021-12-23T15:25:27.924776Z","shell.execute_reply.started":"2021-12-23T15:25:27.189962Z","shell.execute_reply":"2021-12-23T15:25:27.923755Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data = btc.append(eth)\ndata = data.append(iota)","metadata":{"execution":{"iopub.status.busy":"2021-12-23T15:25:27.925962Z","iopub.execute_input":"2021-12-23T15:25:27.926247Z","iopub.status.idle":"2021-12-23T15:25:28.878576Z","shell.execute_reply.started":"2021-12-23T15:25:27.926216Z","shell.execute_reply":"2021-12-23T15:25:28.877374Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data.tail(3)","metadata":{"execution":{"iopub.status.busy":"2021-12-23T15:25:32.493023Z","iopub.execute_input":"2021-12-23T15:25:32.493358Z","iopub.status.idle":"2021-12-23T15:25:32.521878Z","shell.execute_reply.started":"2021-12-23T15:25:32.493323Z","shell.execute_reply":"2021-12-23T15:25:32.520871Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}