{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":59575,"databundleVersionId":8060720,"sourceType":"competition"}],"dockerImageVersionId":30698,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"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":"2024-04-28T15:08:04.101428Z","iopub.execute_input":"2024-04-28T15:08:04.101794Z","iopub.status.idle":"2024-04-28T15:08:08.167626Z","shell.execute_reply.started":"2024-04-28T15:08:04.101764Z","shell.execute_reply":"2024-04-28T15:08:08.166540Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.preprocessing import StandardScaler\nfrom sklearn.impute import SimpleImputer\nfrom sklearn.metrics import accuracy_score\nfrom sklearn.svm import SVC\nfrom sklearn.neighbors import KNeighborsClassifier\nfrom sklearn.linear_model import LogisticRegression\nimport xgboost as xgb","metadata":{"execution":{"iopub.status.busy":"2024-04-28T15:08:08.169691Z","iopub.execute_input":"2024-04-28T15:08:08.170282Z","iopub.status.idle":"2024-04-28T15:08:09.605527Z","shell.execute_reply.started":"2024-04-28T15:08:08.170239Z","shell.execute_reply":"2024-04-28T15:08:09.604209Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_index_patent_ids = pd.read_json(\"/kaggle/input/uspto-explainable-ai/train_index_patent_ids.json\")","metadata":{"execution":{"iopub.status.busy":"2024-04-28T15:08:09.607421Z","iopub.execute_input":"2024-04-28T15:08:09.608233Z","iopub.status.idle":"2024-04-28T15:08:09.723217Z","shell.execute_reply.started":"2024-04-28T15:08:09.608185Z","shell.execute_reply":"2024-04-28T15:08:09.721651Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Display the first few rows of each DataFrame\nprint(\"Train Index Patent IDs:\")\nprint(train_index_patent_ids.head())","metadata":{"execution":{"iopub.status.busy":"2024-04-28T15:08:09.725211Z","iopub.execute_input":"2024-04-28T15:08:09.725737Z","iopub.status.idle":"2024-04-28T15:08:09.737245Z","shell.execute_reply.started":"2024-04-28T15:08:09.725693Z","shell.execute_reply":"2024-04-28T15:08:09.735973Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_index_patent_ids.tail(3)","metadata":{"execution":{"iopub.status.busy":"2024-04-28T15:08:09.741148Z","iopub.execute_input":"2024-04-28T15:08:09.741874Z","iopub.status.idle":"2024-04-28T15:08:09.757655Z","shell.execute_reply.started":"2024-04-28T15:08:09.741833Z","shell.execute_reply":"2024-04-28T15:08:09.756166Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_data = pd.read_csv(\"/kaggle/input/uspto-explainable-ai/test.csv\")","metadata":{"execution":{"iopub.status.busy":"2024-04-28T15:08:09.760241Z","iopub.execute_input":"2024-04-28T15:08:09.761001Z","iopub.status.idle":"2024-04-28T15:08:09.782436Z","shell.execute_reply.started":"2024-04-28T15:08:09.760953Z","shell.execute_reply":"2024-04-28T15:08:09.781196Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import pandas as pd\n\n# Assuming test_data is your DataFrame\nprint(\"\\nTest Data:\")\nprint(test_data.head().to_string(index=False))","metadata":{"execution":{"iopub.status.busy":"2024-04-28T15:08:09.785499Z","iopub.execute_input":"2024-04-28T15:08:09.786481Z","iopub.status.idle":"2024-04-28T15:08:09.818811Z","shell.execute_reply.started":"2024-04-28T15:08:09.786433Z","shell.execute_reply":"2024-04-28T15:08:09.817670Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sample_submission = pd.read_csv(\"/kaggle/input/uspto-explainable-ai/sample_submission.csv\")","metadata":{"execution":{"iopub.status.busy":"2024-04-28T15:08:09.820195Z","iopub.execute_input":"2024-04-28T15:08:09.821288Z","iopub.status.idle":"2024-04-28T15:08:09.832231Z","shell.execute_reply.started":"2024-04-28T15:08:09.821252Z","shell.execute_reply":"2024-04-28T15:08:09.830700Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import pandas as pd\n\n# Assuming sample_submission is your DataFrame\nprint(\"\\nSample Submission:\")\nprint(sample_submission.head().to_string(index=False))","metadata":{"execution":{"iopub.status.busy":"2024-04-28T15:08:09.834461Z","iopub.execute_input":"2024-04-28T15:08:09.835703Z","iopub.status.idle":"2024-04-28T15:08:09.849559Z","shell.execute_reply.started":"2024-04-28T15:08:09.835546Z","shell.execute_reply":"2024-04-28T15:08:09.848204Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"patent_metadata = pd.read_parquet(\"/kaggle/input/uspto-explainable-ai/patent_metadata.parquet\")","metadata":{"execution":{"iopub.status.busy":"2024-04-28T15:08:09.851431Z","iopub.execute_input":"2024-04-28T15:08:09.852157Z","iopub.status.idle":"2024-04-28T15:08:43.089750Z","shell.execute_reply.started":"2024-04-28T15:08:09.852091Z","shell.execute_reply":"2024-04-28T15:08:43.088435Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import pandas as pd\n\n# Assuming patent_metadata is your DataFrame\nprint(\"\\nPatent Metadata:\")\nprint(patent_metadata.head().to_string(index=False))","metadata":{"execution":{"iopub.status.busy":"2024-04-28T15:08:43.091090Z","iopub.execute_input":"2024-04-28T15:08:43.091539Z","iopub.status.idle":"2024-04-28T15:08:43.111062Z","shell.execute_reply.started":"2024-04-28T15:08:43.091500Z","shell.execute_reply":"2024-04-28T15:08:43.110187Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#nearest_neighbors = pd.read_csv(\"/kaggle/input/uspto-explainable-ai/nearest_neighbors.csv\")","metadata":{"execution":{"iopub.status.busy":"2024-04-28T15:08:43.112599Z","iopub.execute_input":"2024-04-28T15:08:43.113287Z","iopub.status.idle":"2024-04-28T15:08:43.117288Z","shell.execute_reply.started":"2024-04-28T15:08:43.113255Z","shell.execute_reply":"2024-04-28T15:08:43.116430Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#print(\"\\nNearest Neighbors:\")\n#print(nearest_neighbors.head())","metadata":{"execution":{"iopub.status.busy":"2024-04-28T15:08:43.119208Z","iopub.execute_input":"2024-04-28T15:08:43.120016Z","iopub.status.idle":"2024-04-28T15:08:43.131235Z","shell.execute_reply.started":"2024-04-28T15:08:43.119984Z","shell.execute_reply":"2024-04-28T15:08:43.130222Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(\"\\nMissing Values:\")","metadata":{"execution":{"iopub.status.busy":"2024-04-28T15:08:43.138532Z","iopub.execute_input":"2024-04-28T15:08:43.141320Z","iopub.status.idle":"2024-04-28T15:08:43.147335Z","shell.execute_reply.started":"2024-04-28T15:08:43.141278Z","shell.execute_reply":"2024-04-28T15:08:43.145969Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(\"Train Index Patent IDs:\\n\", train_index_patent_ids.isnull().sum())","metadata":{"execution":{"iopub.status.busy":"2024-04-28T15:08:43.149538Z","iopub.execute_input":"2024-04-28T15:08:43.150438Z","iopub.status.idle":"2024-04-28T15:08:43.184243Z","shell.execute_reply.started":"2024-04-28T15:08:43.150383Z","shell.execute_reply":"2024-04-28T15:08:43.183050Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(\"Test Data:\\n\", test_data.isnull().sum())","metadata":{"execution":{"iopub.status.busy":"2024-04-28T15:08:43.185828Z","iopub.execute_input":"2024-04-28T15:08:43.186328Z","iopub.status.idle":"2024-04-28T15:08:43.197616Z","shell.execute_reply.started":"2024-04-28T15:08:43.186287Z","shell.execute_reply":"2024-04-28T15:08:43.196288Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(\"Sample Submission:\\n\", sample_submission.isnull().sum())","metadata":{"execution":{"iopub.status.busy":"2024-04-28T15:08:43.199532Z","iopub.execute_input":"2024-04-28T15:08:43.200086Z","iopub.status.idle":"2024-04-28T15:08:43.216816Z","shell.execute_reply.started":"2024-04-28T15:08:43.200041Z","shell.execute_reply":"2024-04-28T15:08:43.215470Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Check for missing values\nprint(\"Patent Metadata:\\n\", patent_metadata.isnull().sum())\n#print(\"Nearest Neighbors:\\n\", nearest_neighbors.isnull().sum())\n","metadata":{"execution":{"iopub.status.busy":"2024-04-28T15:08:43.220309Z","iopub.execute_input":"2024-04-28T15:08:43.221067Z","iopub.status.idle":"2024-04-28T15:08:46.320219Z","shell.execute_reply.started":"2024-04-28T15:08:43.221023Z","shell.execute_reply":"2024-04-28T15:08:46.318880Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Check data types\nprint(\"\\nData Types:\")\n#print(\"Nearest Neighbors:\\n\", nearest_neighbors.dtypes)\n","metadata":{"execution":{"iopub.status.busy":"2024-04-28T15:08:46.321399Z","iopub.execute_input":"2024-04-28T15:08:46.321712Z","iopub.status.idle":"2024-04-28T15:08:46.327649Z","shell.execute_reply.started":"2024-04-28T15:08:46.321685Z","shell.execute_reply":"2024-04-28T15:08:46.326529Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(\"Train Index Patent IDs:\\n\", train_index_patent_ids.dtypes)","metadata":{"execution":{"iopub.status.busy":"2024-04-28T15:08:46.329440Z","iopub.execute_input":"2024-04-28T15:08:46.329829Z","iopub.status.idle":"2024-04-28T15:08:46.345212Z","shell.execute_reply.started":"2024-04-28T15:08:46.329798Z","shell.execute_reply":"2024-04-28T15:08:46.343795Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(\"Test Data:\\n\", test_data.dtypes)","metadata":{"execution":{"iopub.status.busy":"2024-04-28T15:08:46.346667Z","iopub.execute_input":"2024-04-28T15:08:46.347129Z","iopub.status.idle":"2024-04-28T15:08:46.361502Z","shell.execute_reply.started":"2024-04-28T15:08:46.347065Z","shell.execute_reply":"2024-04-28T15:08:46.359855Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(\"Sample Submission:\\n\", sample_submission.dtypes)","metadata":{"execution":{"iopub.status.busy":"2024-04-28T15:08:46.363487Z","iopub.execute_input":"2024-04-28T15:08:46.364000Z","iopub.status.idle":"2024-04-28T15:08:46.376404Z","shell.execute_reply.started":"2024-04-28T15:08:46.363958Z","shell.execute_reply":"2024-04-28T15:08:46.375166Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(\"Patent Metadata:\\n\", patent_metadata.dtypes)","metadata":{"execution":{"iopub.status.busy":"2024-04-28T15:08:46.380662Z","iopub.execute_input":"2024-04-28T15:08:46.381071Z","iopub.status.idle":"2024-04-28T15:08:46.392523Z","shell.execute_reply.started":"2024-04-28T15:08:46.381035Z","shell.execute_reply":"2024-04-28T15:08:46.391076Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import pandas as pd\npatent_data_file = \"/kaggle/input/uspto-explainable-ai/patent_data/1838_4.parquet\"\ndf = pd.read_parquet(patent_data_file)\ndisplay(df.head(5))\n\nprint(f\"Columns in each patent data : {df.columns}\")","metadata":{"execution":{"iopub.status.busy":"2024-04-28T15:08:46.393624Z","iopub.execute_input":"2024-04-28T15:08:46.393998Z","iopub.status.idle":"2024-04-28T15:08:46.432186Z","shell.execute_reply.started":"2024-04-28T15:08:46.393966Z","shell.execute_reply":"2024-04-28T15:08:46.430762Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Use the ls command to list the contents of the directory\n!ls /kaggle/input/uspto-explainable-ai","metadata":{"execution":{"iopub.status.busy":"2024-04-28T15:08:46.433750Z","iopub.execute_input":"2024-04-28T15:08:46.434244Z","iopub.status.idle":"2024-04-28T15:08:47.654726Z","shell.execute_reply.started":"2024-04-28T15:08:46.434199Z","shell.execute_reply":"2024-04-28T15:08:47.653533Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Import the pandas library as pd\nimport pandas as pd\n\n# Define the file path of the patent data file\npatent_data_file = \"/kaggle/input/uspto-explainable-ai/patent_data/1838_4.parquet\"\n\n# Read the patent data file into a DataFrame using pandas\ndf = pd.read_parquet(patent_data_file)\n\n# Display the first 5 rows of the DataFrame\ndisplay(df.head(5))\n\n# Print the columns present in the DataFrame\nprint(f\"Columns in each patent data : {df.columns}\")","metadata":{"execution":{"iopub.status.busy":"2024-04-28T15:08:47.656681Z","iopub.execute_input":"2024-04-28T15:08:47.657052Z","iopub.status.idle":"2024-04-28T15:08:47.686197Z","shell.execute_reply.started":"2024-04-28T15:08:47.657018Z","shell.execute_reply":"2024-04-28T15:08:47.684648Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Import the os module to interact with the operating system\nimport os\n\n# List the files in the specified directory\nfiles = os.listdir(\"/kaggle/input/uspto-explainable-ai/patent_data\")\n\n# Print the total number of files\nprint(f\"Total files : {len(files)}\")","metadata":{"execution":{"iopub.status.busy":"2024-04-28T15:08:47.688558Z","iopub.execute_input":"2024-04-28T15:08:47.689137Z","iopub.status.idle":"2024-04-28T15:08:47.710027Z","shell.execute_reply.started":"2024-04-28T15:08:47.689062Z","shell.execute_reply":"2024-04-28T15:08:47.707291Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Initialize an empty list to store years\nyears = []\n\n# Iterate through the list of files\nfor i in files:\n    try:\n        # Split the file name by \"_\" and extract the year part\n        year = int(i.split(\"_\")[0])\n        # Append the extracted year to the years list\n        years.append(year)\n    except:\n        # If an error occurs during conversion to int, print the file name\n        print(i)\n\n# Convert the list of years to a set to remove duplicates, then convert it back to a list\nyears = list(set(years))\n\n# Print the oldest and latest years found in the file names\nprint(f\"Oldest year : {min(years)}\")\nprint(f\"Latest Year : {max(years)}\")\n","metadata":{"execution":{"iopub.status.busy":"2024-04-28T15:08:47.713137Z","iopub.execute_input":"2024-04-28T15:08:47.713606Z","iopub.status.idle":"2024-04-28T15:08:47.727492Z","shell.execute_reply.started":"2024-04-28T15:08:47.713570Z","shell.execute_reply":"2024-04-28T15:08:47.726168Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import pandas as pd\n\n# Read the patent metadata from the Parquet file\nmetadata = pd.read_parquet(\"/kaggle/input/uspto-explainable-ai/patent_metadata.parquet\")\n\n# Display the first few rows of the metadata DataFrame\nmetadata.head()","metadata":{"execution":{"iopub.status.busy":"2024-04-28T15:08:47.729460Z","iopub.execute_input":"2024-04-28T15:08:47.729928Z","iopub.status.idle":"2024-04-28T15:09:19.700950Z","shell.execute_reply.started":"2024-04-28T15:08:47.729882Z","shell.execute_reply":"2024-04-28T15:09:19.699634Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"metadata_shape = metadata.shape\nprint(\"Number of rows:\", metadata_shape[0])\nprint(\"Number of columns:\", metadata_shape[1])","metadata":{"execution":{"iopub.status.busy":"2024-04-28T15:09:19.702285Z","iopub.execute_input":"2024-04-28T15:09:19.702674Z","iopub.status.idle":"2024-04-28T15:09:19.709635Z","shell.execute_reply.started":"2024-04-28T15:09:19.702641Z","shell.execute_reply":"2024-04-28T15:09:19.708189Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"metadata.columns","metadata":{"execution":{"iopub.status.busy":"2024-04-28T15:09:19.711246Z","iopub.execute_input":"2024-04-28T15:09:19.711609Z","iopub.status.idle":"2024-04-28T15:09:19.727752Z","shell.execute_reply.started":"2024-04-28T15:09:19.711580Z","shell.execute_reply":"2024-04-28T15:09:19.726184Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Iterate over each column in the metadata DataFrame\nfor col in metadata.columns:\n    try:\n        # Try to calculate the total number of unique values for the current column\n        print(f\"Total unique values of column {col} : {metadata[col].nunique()}\")\n    except:\n        # If an error occurs (e.g., non-numeric data), print an error message\n        print(f\"Can't find unique values of column {col}\")","metadata":{"execution":{"iopub.status.busy":"2024-04-28T15:09:19.729685Z","iopub.execute_input":"2024-04-28T15:09:19.730518Z","iopub.status.idle":"2024-04-28T15:09:39.114156Z","shell.execute_reply.started":"2024-04-28T15:09:19.730469Z","shell.execute_reply":"2024-04-28T15:09:39.112894Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"nn = pd.read_csv(\"/kaggle/input/uspto-explainable-ai/nearest_neighbors.csv\",nrows=100)\nnn.head()","metadata":{"execution":{"iopub.status.busy":"2024-04-28T15:09:39.115783Z","iopub.execute_input":"2024-04-28T15:09:39.116739Z","iopub.status.idle":"2024-04-28T15:09:39.161383Z","shell.execute_reply.started":"2024-04-28T15:09:39.116704Z","shell.execute_reply":"2024-04-28T15:09:39.160154Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"tr_idx = pd.read_json(\"/kaggle/input/uspto-explainable-ai/train_index_patent_ids.json\")\ntr_idx","metadata":{"execution":{"iopub.status.busy":"2024-04-28T15:09:39.162815Z","iopub.execute_input":"2024-04-28T15:09:39.163276Z","iopub.status.idle":"2024-04-28T15:09:39.233298Z","shell.execute_reply.started":"2024-04-28T15:09:39.163241Z","shell.execute_reply":"2024-04-28T15:09:39.232031Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test = pd.read_csv(\"/kaggle/input/uspto-explainable-ai/test.csv\")\ntest.head()","metadata":{"execution":{"iopub.status.busy":"2024-04-28T15:09:39.234685Z","iopub.execute_input":"2024-04-28T15:09:39.235606Z","iopub.status.idle":"2024-04-28T15:09:39.264893Z","shell.execute_reply.started":"2024-04-28T15:09:39.235571Z","shell.execute_reply":"2024-04-28T15:09:39.263649Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sub = pd.read_csv(\"/kaggle/input/uspto-explainable-ai/sample_submission.csv\")\nsub.head()","metadata":{"execution":{"iopub.status.busy":"2024-04-28T15:09:39.266228Z","iopub.execute_input":"2024-04-28T15:09:39.266574Z","iopub.status.idle":"2024-04-28T15:09:39.281281Z","shell.execute_reply.started":"2024-04-28T15:09:39.266543Z","shell.execute_reply":"2024-04-28T15:09:39.279658Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sub.isnull().sum()\n","metadata":{"execution":{"iopub.status.busy":"2024-04-28T15:21:37.947115Z","iopub.execute_input":"2024-04-28T15:21:37.949651Z","iopub.status.idle":"2024-04-28T15:21:37.970506Z","shell.execute_reply.started":"2024-04-28T15:21:37.949573Z","shell.execute_reply":"2024-04-28T15:21:37.969426Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test.isnull().sum()","metadata":{"execution":{"iopub.status.busy":"2024-04-28T15:22:13.534442Z","iopub.execute_input":"2024-04-28T15:22:13.535728Z","iopub.status.idle":"2024-04-28T15:22:13.547165Z","shell.execute_reply.started":"2024-04-28T15:22:13.535685Z","shell.execute_reply":"2024-04-28T15:22:13.545544Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sub.to_csv(\"submission.csv\", index=False)","metadata":{"execution":{"iopub.status.busy":"2024-04-28T15:23:32.054501Z","iopub.execute_input":"2024-04-28T15:23:32.055052Z","iopub.status.idle":"2024-04-28T15:23:32.066033Z","shell.execute_reply.started":"2024-04-28T15:23:32.055012Z","shell.execute_reply":"2024-04-28T15:23:32.064314Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}