{"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":"from glob import glob\nimport glob\nfrom tqdm import tqdm\nimport pandas as pd\nimport numpy as np\nimport matplotlib.pyplot  as plt\nimport plotly.express as px\nimport seaborn as sns\nimport collections","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train=glob.glob('C:/Users/kvenkatesh3/Downloads/Kaggle DS/smartphone-decimeter-2022/train/*')","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train[0]","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train1=glob.glob(train[0] + '/*')","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print (train1)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"file=glob.glob(train1[0] + '/*')","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(file)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"device_gnss=glob.glob(train1[0] + 'device_gnss')","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"device_imu=glob.glob(train1[0] + 'device_imu')","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"for k in file:\n    print(k)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train=glob.glob('C:/Users/kvenkatesh3/Downloads/Kaggle DS/smartphone-decimeter-2022/train/*')\ndevice_gnss = pd.DataFrame()\n\n\n#collection_name=[]\n#device_name=[]\n\nfor h in tqdm(train):\n    train_ = glob.glob(h + '\\\\*')\n    #col = h.split('/')[5]\n    for i in train_:\n        collection=i.split('/')[6].split('\\\\')\n        \n\n        device_gnss_ = glob.glob(i + '\\\\device_gnss.csv')\n        device_imu_ = glob.glob(i +'\\\\device_imu.csv')\n        device_gnss_df = pd.read_csv(device_gnss_[0])\n        device_imu_df =pd.read_csv(device_imu_[0])\n        common_pts=len(set(device_gnss_df['utcTimeMillis']).intersection(set(device_imu_df['utcTimeMillis'])))\n        common=set(device_gnss_df['utcTimeMillis']).intersection(set(device_imu_df['utcTimeMillis']))\n\n        gnss_pts=len(set(device_gnss_df['utcTimeMillis']))\n        imu_pts=len(set(device_imu_df['utcTimeMillis']))\n        print('Collection', collection[1], 'device', collection[2])\n        print('GNSS',gnss_pts,'IMU' ,imu_pts,'Common' ,common_pts)\n        print('--------------------------------------------------------')\n        \n        #common_gnss=device_gnss_df[device_gnss_df['utcTimeMillis'].isin(common)]\n        #common_imu=\n        \n        #common_merge= pd.merge(common_gnss, common_imu, on='utc')\n        #device_gnss_df['collection_name'] = collection[1]\n        #device_gnss_df['device_name'] = collection[2]\n        #device_gnss=device_gnss.append(device_gnss_df).reset_index(drop=True) \n        \n        ","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"collection=i.split('/')[6].split('\\\\')","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"device_gnss_df","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"collection","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"device_gnss_df.tail()","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"device_gnss_df=pd.read_csv(\"C:/Users/kvenkatesh3/Downloads/Kaggle DS/smartphone-decimeter-2022/train/2020-05-15-US-MTV-1/GooglePixel4XL/device_gnss.csv\")","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"device_gnss_df.head()","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"device_gnss_df.describe","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"device_imu = pd.DataFrame()\n\n\n#collection_name=[]\n#device_name=[]\n\nfor h in tqdm(train):\n    train = glob.glob(h + '/*')\n    #col = h.split('/')[5]\n    for i in train:\n        collection= i.split('/')\n        \n        \n        #device_imu\n        device_imu = glob.glob(i + '/device_imu.csv')\n        device_imu_df = pd.read_csv(device_imu[0])\n        device_imu_df['collection_name'] = collection[4]\n        device_imu_df['device_name'] = collection[3]\n        device_imu=device_imu.append(device_imu_df).reset_index(drop=True) \n        \n        ","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"device_imu_df=pd.read_csv(\"C:/Users/kvenkatesh3/Downloads/Kaggle DS/smartphone-decimeter-2022/train/2020-05-15-US-MTV-1/GooglePixel4XL/device_imu.csv\")","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"device_imu_df.head()","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"device_imu_df.tail()","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"device_gnss_df.shape","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"device_imu_df.shape","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"device_gnss_df.count()","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"device_imu_df.count()","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"device_gnss_df.isna()","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"device_imu_df.isna()","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"device_gnss_df.utcTimeMillis.hist()\nplt.show()","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"device_imu_df.utcTimeMillis.hist()\nplt.show()","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train=glob.glob('C:/Users/kvenkatesh3/Downloads/Kaggle DS/smartphone-decimeter-2022/train/*')\ndevice_imu = pd.DataFrame()\n\n\n#collection_name=[]\n#device_name=[]\n\nfor h in tqdm(train):\n    train_ = glob.glob(h + '\\\\*')\n    #col = h.split('/')[5]\n    for i in train_:\n        collection=i.split('/')[6].split('\\\\')\n        \n\n        device_imu_ = glob.glob(i + '\\\\device_imu.csv')\n        device_imu_df = pd.read_csv(device_imu_[0])\n        device_imu_df['collection_name'] = collection[1]\n        device_imu_df['device_name'] = collection[2]\n        device_imu=device_imu.append(device_imu_df).reset_index(drop=True) \n        ","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}