{"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":"markdown","source":"# Open Problems - Multimodal Single-Cell Integration - EDA","metadata":{}},{"cell_type":"markdown","source":"**This is my first trial at an EDA. I hope it is helpful and informative. Please feel free to critique it and give me tips in order to improve. Thank you in advance!!**\n\n**This is also a work-in-progress. If aspects need clairification, please let me know. My understanding of biology is very minimal, so feel free to point out anything that may be incorrect or misleading.**\n\n**Also, if you find it insightful please consider upvoting!**","metadata":{}},{"cell_type":"markdown","source":"# Problem Description!\n\nThe objective of this competition is to understand the relationship between different modalities in cells. In this notebook, we are trying to understand the data that is given. This information will help us make an ideal model.\n\nOne of the main challenges as far as data goes is that the test set contains data from a much later time period than the data of the train set.\n\nAlso, I could not have done this without the help of previous EDA makers for the competition. Most notabley: https://www.kaggle.com/code/vicsonsam/multisci-eda was essential for my understanding of the competition, so please consider giving them an upvote, as well.","metadata":{}},{"cell_type":"markdown","source":"# About the datasets","metadata":{}},{"cell_type":"markdown","source":"**Cell Types:**\n\nMasP = Mast Cell Progenitor\n\nMkP = Megakaryocyte Progenitor\n\nNeuP = Neutrophil Progenitor\n\nMoP = Monocyte Progenitor\n\nEryP = Erythrocyte Progenitor\n\nHSC = Hematoploetic Stem Cell\n\nBP = B-Cell Progenitor","metadata":{}},{"cell_type":"markdown","source":"**metadata.csv**\n\ncell_id - A unique identifier for each observed cell.\n\ndonor - An identifier for the four cell donors.\n\nday - The day of the experiment the observation was made.\n\ntechnology - Either citeseq or multiome.\n\ncell_type - One of the above cell types or else hidden.","metadata":{}},{"cell_type":"markdown","source":"# Evaluation metric used","metadata":{}},{"cell_type":"markdown","source":"For this competition, the Pearson Correlation Coefficient metric will be used (PPC)\n![image.png](attachment:7f422a81-a229-49be-96c4-f9ec4d8514aa.png)!\nAt it's core, the Pearson Correlation Coefficient is a measure of linear correlation between 2 sets of data.\n\nTo better understand PPC, visit the wikipedia page: https://en.wikipedia.org/wiki/Pearson_correlation_coefficient","metadata":{},"attachments":{"7f422a81-a229-49be-96c4-f9ec4d8514aa.png":{"image/png":"iVBORw0KGgoAAAANSUhEUgAAA8AAAAISCAIAAACMNTFcAAAgAElEQVR4nO3df2zb953n+ReL3qFsrpN66Nrtxk2pzsHBuOk2GxKNc2MlcbKgsPbJzYGcRWzUKbZuRLdoES/sO0CEk8JxIO3d2YcELTYREy+wzsAKMCRuGiEqSOzYSeUg6oDsNmirRTQzFdsq20j1t6m3cFXsAav745v9mqEoil/yS36+/H6fDwwGFK2Q7xno8/m+vp/v50dkfX1dAAAAANrzIdMFAAAAAIOEAA0AAAC4QIAGAAAAXCBAAwAAAC4QoAEAAAAXCNAAAACACwRoAAAAwAUCNAAAAOACARoAAABwgQANAAAAuECABgAAAFwgQAMAAAAuEKABAAAAFwjQAAAAgAsEaADA1iKRiOkSAMAvCNBhx0URAADAFQI0AAAA4AIBGgAAAHCBAA0AAAC4QIAGAAAAXCBAAwAAAC4QoAEAAAAXCNAAAACACwRoAAAAwAUCNAAAAOACARoAAABwgQANAAAAuECABgAAAFwgQAMAAAAuEKABAAAAFwjQAAAAgAsEaAAAAMAFAjQAAADgAgEaAAAAcIEADQAAALhAgAYAAABcIEADAAAALhCgAQAAABcI0AAAAIALBGgAAADABQI0EGqLi1YkciYSOXP+/JumawEAYDAQoIHwunx56Y47vmu/vu22j5ktBkD3wnBLfP36H19++aeHDk1HImcOHZp++eWfmq4IYfRh0wUAMOOFF340Njbj/Pjnf77dYDEAunf58tJDD120Xwf1lvitt969664p58eZmcWZmcVLl37y0kv/2623fsRgYQgbRqCB0FlctA4dmq5Pz5Ki0f/BVD0AuvfCCz9y0rMCeks8P79cn54dMzOLR4/+v/2vB2FGgAZCZHX1xvnzb95xx3dnZhYb/mn37piRkgB0qftb4rfeetdXUz6a1rO4aN177wX79ejo7pWVU+vr356eTtvvzMwszs8v97VKhBtTOABvXL/+x+9//x9ef/0Xzz9fkXT69PD+/UMPPjhkuq6bVldv7Nx5ruk/nT493OdiAHRvcdGamVk8daq88Z/avCV+6613n3++avdaJ0/e63F97rWop/62/9y51I4dt0h65JE7Dx8u2m++8cav9u7d1cdiEWoEaMADDdPyJD399NzTT88dP578N//moS1n5kUiZ9r8ovX1b3dYonT58pL9YnR094kTe1dXbzgXns99bkfHHwvAiOvX/+gsAm6w5S3x9et/rFZ//cwz8xsfRrX/7R4OGWxZz+Ki5dwnnDuXanp7cOpU2Q/3AAgJAjTQrcVFq+m0PEn2peW55w72t6Lm3nnn99PT6bvv/pR97alfum6P5QAYIN///j/YL0ZHdx858vkdO25x5kC3uCW2g69z89yZFkMGZ8484Ko/abOe11//hfP6n/9zHz3ZQ2gRoIFuOeMip08Pf+tb9+zYcYs9WGIPpTz/fOUrX/mCHx4sNozNvPPO753Xd97JCDQwYNzeEm823+P48aSrPsqrIQNX9dTP8P7CFz7ZZqlA7xCgga5cvrzkPHO007Ok3btj586lnPe3nJnXzcSMjtVftxiBBgZOi1viXbv+pP6f3nrr3UJh4emn5xo+YXo6/eCDQ26bf/2QwdGjX9i9O7a6euNrX3ul/SEDt/W89da7zuuG2SmLi5bzenR0t6v/Q4BuEKCBrvz1Xy/YL/L50fp+v36Kng9n5q2u3nBeHz+eNFgJAE/U3xI3TBFuGDB2O+Rcr+mQwY4dt7gaMnBbj2WtOa/37//A/I3f/vbmP91/f7zd/zOArhGggc6trt6wH1lK+uIX/0nHn+PJIsLr1//48Y//nw1vHj+ebPo49ec/f895fffdn2rz2wH4U/u3xNPT6UceubPjL/J8yKCdev7jf7w5Av3Rj35ge77f/OYPzuugnh0DfyJAA52rj6Hx+Mfr/+n69T/2uZha7Xcb37z//s80/eU//OH/c17/2Z9t61VNADrl6pb417++OX+j9S3x4cPF11//xV/+5Z4779zhdvKGV0MGbut5/fWa8/qzn/1Af/V3f3dz72fGAtBPHKQCdO4nP1l1XjfsVVcfZ8+dS/WhmP/0n65tfLMh1jvqR3QapksC8ANXt8T1kxw23hK/+eax+l7o+ecrDz10cefOcy+88KP6OcRb8mrIwG099XvbNYTs+onUnAaFfmIEGujcj370683+6T/8hyXn9T/7Z1usGfdkEWH9Nk+OzaYV1o/ofHr3R7v/dgDeanpLvNkB3fW3xBs31dm7d9fevbuOHv2n3/ve2/XbWdiv258S3WLIoL7aLYcMvKqn/ujBfH50y98HPMQINNA552mmPrgY/K233q1f0NOfId7nnju4vv7thv9p+purqzecEZ3R0d1RRftQHgBXmt4Sb/ZMqf6WeDM7dtzy2GN3r6ycco6/tj3/fOXeey8cOjS95Se0GDJ4441fOa+3HDLwqp76QP/5z7MXJ/qKAA10qH7VjqSXXnrLfjE/v/zEE1ec9/P5Ub89WPzd724+bGXdOuBPTW+Jmx5r2nBL3Hpm844dtzzyyJ3r69/+2799tH7ft3aOJKwfMqjvAOfnl+uHDFztK99OPfVD2s73rq7ecEavjx9P+mGvfYQKARro0E9/ulr/49NPz0UiZyKRM/fee8Hp+k+fHn7ssbtNVNfK8vJ/cV63OVYEwLc6uyV+8MGhV145/Pbb32xzI8uG2cnf+c4P7Sy7uGhNTNyciNywO0f7WtTzF3/xaef15ctLklZXb3znOz903jxz5oEOvhHoBnOggQ794z/eXE+Tz4/Wz+SznT49fPbsg/0tqi2sIASCpJtb4t27Y889d/ArX/lC/RyMLb9F//3s7obf6X7IoGk9e/fuGh3dbQ9MHD5cbDj3+5VXDnMUFPqPEWigQ/XTAb/0pTtWVk45q1hOnx5+881j/kzP+uB0yY9/vMkTYQADpPtb4r17d225c3PDkMHGX/BwyGBjPS++eKjpQYOvvHKYAwhhRGR9fd10DTApEuFvoEP1p58YOYsb6Cf6Ct86dGjamTa2snKqR8OxX//6q84c6JWVU5KcPTROnx4+eHB3r2chr67euHx56dKln8zMLI6O7j5y5PMdnEMOeIUOMey4KHZmcdG6447v2q/PnUv57aRuwHP0FSHnwyGDNa2xiRBMYQoH0In66YB+22QDALxVv4KwPydDtYP0DIMI0EAn6qcDfuITHEQCIMjqhwxuu+1jBisBfIJdOIBOPPbY3T7cnw4AeqF+yODuuz9lsBLAJxiBBgAArdRvOvTxj39kTWsGiwH8gEUhYcfCIADtoK8AAAcj0AAAAIALBGgAAADABQI0AAAA4AIBGgAAAHCBAA0AAAC4QIAGAAAAXCBAAwAAAC4QoAEAAAAXCNAAAACACwRoAAAAwAUCNAAAAOACARoAAABwgQANAAAAuECABgAAAFwgQAMAAAAuEKABAAAAFwjQAAAAgAsEaAAAAMAFAjQAAADgAgEaAAAAcIEADQAAALhAgAYAvC+n3IhGTFcBAH4XWV9fN10DTIpE+BsA8L7t2m7JGtPYlKYa/om+AgAcjEADAN5XUklSXvm88qZrAQD/YkQh7BhVAlCvrLI9i6OiSkIJ5336CgBwMAINALgppdS4xiWNaMSSZbocAPAjRhTCjlElABuNaKSsckKJiir2O/QVAOBgBBoA0OiSLsUVr6qaVdZ0LQDgOwRoAECjmGJXdCWmGAsKAWAjHsmFHY9lAWymfkFhMpKkrwAAGyPQAIDmUkpNaEJSUkn9ielqAMA3GH0MO0agAbSWUaaoopa1vou+AgAkRqABAK0VVEgooV3KKGO6FgDwBQI0AGALBRVkqajipCZN1wIA5vH4PuyYwgGgHZF7I3pTkgoqpJU2XQ4AmER4CjsCNABJ712I1P+47VhjtxCJRKbWp7LKxhSrqBJXvJ/fDgC+whQOAAi7hvza9B1JYxob05gla7/2e3jKd5vfDgD+wehj2DECDYRci7RaPxLs9BVJJauqppQqqdS3bwcAX2EEGgDgQkmlmGJllXPKma4FAMwgQAMAXIgpZo89T2qyqKLpcgDAAAI0AMCdhBIXdVFSRpmqqqbLAYB+I0ADAFw7qqNjGpOUUcbDBYUAMBBYQBZ2LCIE0HQlX8MavqZ9xYhGyirv076yylFFe/ftAOArjEADQNhtTKtt5tdLurRLu67q6rjG+//tAGAKo49hxwg0gHZs1lfUVBvSkKQpTdmTOgAg8BiBBgB0Lq54QQVJWWVZUAggJAjQAICupJW2p3CMaGRFK6bLAYCe4/F92DGFA0A7tuwr7AWFCSUqqvStKgAwghFoAIAHSirFFa+qmlHGdC0A0FsEaACAN67oSlTRoop55U3XAgA9RIAGAHgjrvjf6G8kZZUtq2y6HADoFQI0AMAzKaUmNCHpYT3MgkIAQcUCsrBjESGAdrjqKzLKFFWMK15RJaZYTwsDgP4jPIUdARpAO9z2FUMaqqmWVtreJRoAgoQpHAAA79ljz0UVz+qs6VoAwGOMPoYdI9AA2tFBX1FWeUQjkkoqpZTqTV0AYAAj0ACAnkgpNaUpSQ/r4QUtmC4HADzD6GPYMQINoB0d9xWP6tGX9FJc8QUtRBX1vDAA6D/CU9gRoAG0o5u+IqlkVdV92jenOW+rAgAjmMIBAOitkkoxxa7qak4507UAgAcYfQw7RqABtKPLvqKqalJJSQUV0kp7VxcAGMAINACg5xJKXNRFSRllWFAIYNARoAEA/XBUR8c1Luk+3ccp3wAGGo/vw44pHADa4VVfYS8oTClVUqn7TwMAIxiBBgD0z5zm4oqXVc4qa7oWAOgQARoA0D9RRQsqSMorn1fedDkA0Ake34cdUzgAtMPbvmJWswd1UNKc5vZpn1cfCwD9wQg0AKDfDuiAvaDwYT1syTJdDgC4w+hj2DECDaAdvegrRjRSVnmP9lRU4ZRvAAOEEeiAq6lmugQAaK6kUlzxBS2c0AnTtQCACwToIJvU5JCGssoSowH40xVdiSmWV35Sk6ZrAYB2EaCD7Pf6vaS88sRoAP4UV9w+oTCn3FVdNV0OALSFAB1kE5q4pmv2Sh07RmeUqapqui4AuOmADkxoQtKwhrnPBzAQWEAWCpasvPI55ewfU0pNaCKhhFhECKA9ve4rMsoUVWRBIYCBQHgKl0lNntd5e9OohBJTmkpGkvwNANhSH262P6fPLWjhgA68qld7+kUA0CWmcITLuMav6dqEJmKKVVVNKqmKyiqbrgsAdFmXo4rOapYFhQB8jhHo8LIndTij0eMaTyttuigAPtWf6V7v39hLBRXokQD4FgE67CKZSLwQtxfuxBU/p3NctABs1Lf1Es/q2RM6EVPsB/rBHu3pwzcCgFsE6LCzL4pFFU/plBOjxzU+pjFJ712I1P/ytmP8tQAh1c8Fx1ll88rHFa+oElOsP18KAO0jQIdd/UWxqOKkJu197mKK/f0Fa+Pvk6GBcOrzjj1JJauqppQqqdS3LwWANrGIEDella6oUlIpoUTT9KwNY9IA0AsllWKKlVV29t8EAP9gBDrsNhtVahGUGYQGQqj/e8azoBCAbzECDQDwo4QS9infHKEKwG8I0HDthE7Ym98BQE8d1VF7QfPDephuB4B/EKDh2rN6dru2Z5W1d+0AgN6Z0lRKqWUtP6yH17RmuhwAkJgDjRbzGptOg75+bOlJPfmSXrJ/PKqjT+mpuOJN/xNmSwOB0f850A5L1l26a1nLj+vxZ/SMkRoAoB4BOuxaXxQ3C8SWrPM67xy3m1Z6XOOfvZDc+AlkaCAYDAZoSTXVhjQkaUpT9qQOADCIAB123VwULVlndTav/JrWfnth018jQwMBYDZASyqqmFFGUkWVhBIGKwEA5kCjczHFntEzv9KvntJTpmsBEHD2ky5JIxpZ0YrpcgCEGiPQYefVqBL7RgPBZnwE2jaikbLKCSUqqpiuBUB4MQINABgYJZXiildVtadzAIARBGj03JCGZjVrugoAAXFFV6KKFlXMK2+6FgAhRYCGNzabp3H3sXhNtYM6OKQhrnYAuhdX/G/0N5KyypZVNl0OgDAiQMMzGzP0tmPrS1oqqBBXvKZaVlliNIDupZSa0ISkh/UwCwoB9J8vFoXAoL4tDJrV7JN6sqqqpJhiT+iJMY1FFe3DVwPonk8WEdbLKFNUMa54RZWYYqbLARAivusQ0Wd9viiWVc4p58Tokzp5QieI0YD/+TBASxrSUE21tNIFFUzXAiBEmMKBvkopVVFlTnMppSxZOeViik1q0pJlujQAg8ceey6qeFZnTdcCIET8OKKAfjI4qlRVNaecvQYoqui4xr+hb/AcFvAnf45ASyqrPKIRSSWVUkqZLgdAKDACDWMSSpRU+pl+llZ6TWtP6snt2p5VliVBANqXUmpKU5Ie1sP29DAA6DWfjiigb3wyqlRT7ZROFVW0fxzT2FN6aqd2mq0KgMMnfcVmssrmlY8rvqAFllUA6DVfd4joA19dFFe08qSedPa5Syt9TufiiputCoB81lc0lVSyquo+7ZvTnOlaAAQcUzjgIzu1c0pT13RtTGOSiioOaSijTE0106UB8LuSSjHFrupqTjnTtQAIOL+PKKDXfDuqZMk6r/N55e0NOuxzExJKmK4LCCnf9hX1qqomlZRUUCGttOlyAATWAHSI6CmfXxTtGD2pSftHYjRgis/7CsdLeulRPSrpZ/rZHu0xXQ6AYGIKB3wtptiEJta1PqGJmGJllZNKJpW0N78DgAZHdXRc45Lu031s6QOgRwZjRAG9MyijSrZJTZ7XeXtSR0KJCU2w7SvQH4PVV9gLClNKlVQyXQuAABqkDhG9MFgXRVte+ZxydoyOK35O55jsCPSah33Fexci9T9uO+Z9F7SmtT3aU1NtTGP2LtEA4CGmcGDwjGnsmq5d1MW44jXVMsoMacjZQxqAnzWk56bvdC+qaEEFSXnlnZ0xAcArgzf6CG8N4gh0vaKKp3TK3ucurvi4xtNKcx444DlP+ooWWbkX49Czmj2og5LmNLdP+zz/fAChxQg0Blta6SUtFVRIKFFTLavsXborr/ya1kyXBsCwAzpgLyh8WA/bk74AwBMEaARBWumKKiWVEkosazmr7Kf16UlNcskEQs5eamzJuk/3cV8NwCsEaARHSqmKKhVVEkpYsnLK3aE7iNFAyJVUiiu+oIUTOmG6FgABQYBG0CSUsGO0PeyUU267tueUY0dYILSu6EpMsbzyzqlMANCNwV5Ahu4N+iLC1qqqTmrS2aDjcT3+hJ5giSHQAa/6iqbrCHuxgrCBs6CwpBL7xwPoUpDDE9oR7ABtq6k2qUlnK6sxjY1rPK642aqAwTJY+0A3NanJnHJRRRe0QA8AoBvBD09oLQwB2tYQo4/q6FN6ioso0KZg9BUZZYoq7tGen+lnpmsBMMCC0CGiG8G4KLbPknVWZ5/Vs/aPaaXHNZ5QwmxVgP8Fpq/4nD63oIXOTvk2NXYOwG9YRIhwiSn2jJ65pmuP6/GookUVk0pmlKmqaro0AP3wA/0gqmhZZbcLCvtzhiKAgRCQEQV0LDCjSh2wZOWVzyln/5hS6gk9wXFlQFNB6iuqqiaVlFRQIa10O/9Jn89QBOBzjEAjvGKKjWt8XetP6amYYmWVhzWcVPKqrpouDUAPJZR4Rs9Iyiq7oAXT5QAYPARoQE/oiWu6NqWpmGJVVe0YPatZ03UB6JXH9fiYxixZB3WQs5YAuEWABt43prFruvaMnrFj9EEdHNKQs4c0gICZ0lRCiZpqR3TEdC0ABgwBGviAx/X4NV0rqBBXvKZaRpkhDTmb3wEIkpJK9vQtZy0EALQjOItC0JkgLQzyXFHFUzpVU01SXPFxjY9pzHRRgBlB7SvaX1Bo6gxFAD7ECDSwqbTSS1p6Va/az3mzym7X9rzyzJgEAiOhxJSmJG25neXGrEx6BkIrmCMKaF9QR5U8Zz/kta+vMcVO6uS4xk0XBfRPsPuKEzrxrJ7dpV0/1o9jipkuB4DfBblDRDuCfVH0XFXVnHJlle0fn9JT39A3uNwiDALfV4xopKxyQok5zUUVNV0OAF8LeIeILQX+otgL9TE6qugJnTipk8RoBFvg+wpL1l26a1nLj+txe5doANhMwDtEbCnwF8Xeqal2Sqecfe7GNPaUntqpnWarAnokDH1FTbUhDUma0hQrhgG0wCJCoENxxQsqLGnJXrmfV/6T+mRWWXvXDgADx27UkrLKtl5QCCDkgj+igNbCMKrUBytaeVJPOttFp5U+p3NxxbVh6yuW7WNAhaevyCk3qcmYYhVV7FYMAA3C0iFiM+G5KPaBJSunXH2MfuFCk4MMydAYRKHqK5wFhRVVTNcCwI9C1CGiqVBdFPvDknVe5/PK//2FTbeLJkNj4IStrxjSUE21tNL2pA4AqMccaMBjMcUmNPG23jZdCIDOXdGVmGJFFZ1nSgDgIEADPcGudsBAiyt+SZckZZV1tn4HABsBGjCA6zHgfymlJjQh6YiOsLsOgHoEaMCAEY0MacjZQxqAP41rPK20JWu/9lvadFUDgLAhQAO9stlKwb8+NhVXvKZaRhliNOBzBRXsBptV1nQtAPyCAA300MYMve3Y+pjGlrTkXJXtGJ1XnvEtwJ8qqtgLCic1aboWAL4Qrm2JsFHYtqbyG/uSbJ95Zm/fwQHC8Kcw9BUtjj0qqzyiEUkllVJK9bsyAD4T/A4RrYXhouh/ZZVzyjkx+qROjmmMfTzgK4HvKxrSs60+Q+eVt2dxVFRJKNG/ygD4T8A7RGwp8BfFAVJVNassMRr+FOy+oml6ttVn6KyyeeXjii9pqS91AfAp5kADfmGfG1xRJaWUfSr4dm3PKbeiFdOlAZCkKU0llKipllTSdC0ATCJAA/6SUKKkUkWVtNKSJjX5SX3yhE6wxBDwg5JKMcWqquaUM10LAGMI0IAfJZQoqLCkJXtN4bN6dru2Z5XlNAfArJhiP9APJE1qkj0ogdAiQAP+FVd8SlNOjM4rP6ShR/UoMRowaI/2TGlKUkYZGiMQTgRowO/sGH1N1x7X45Je0ktDGsooYy83BNC9zY492uz9MY2Na1xSUkkyNBBCQV5VjXYEe2V98FiyzupsXvk1rUlKKz2ucXbUQh+Eoa9osQ90U0klq6qmlCqp1Mu6APhO8DtEtBaGi2LwWLLyyjtrmFJKPaEn9mmf2aoQbPQVG61pbY/21FQb05g9qQNASNAhhh0XxYF2Vmef1bP2Bh0JJSY0wRlp6BH6iqaqqtpb2k1pimNEgfCgQww7LooBYI9GE6PRWiSy6Vkh6Mp+6bJkSf+rNG+6GHiEKyNaIzwNPC6KeN+/kv5vvX9wYVX636UrhivyIXq8jnGz3UJOuUlNxhR7W29zeigQBnSIYcdFMWCKKp7SKXtbgLji53TOPpAF6BJ9RWsjGimrbJ8naroWAD3HNnZAoKSVXtJSQYW44jXVMsoMaYjjHoBeK6kUV7yqalZZ07UA6DkCNBBAdowuqZRQwo7R27U9r7zpuoAgu6IrMcXyytPWgMDjkVzY8Vg28Moq55SzT12JKXZSJ+0DIABX6CvaUVZ5RCOSSiqxlhcIMDrEsOOiGBJVVXPKlVW2f5zQxJjGWO2E9tFXtGlSkznlYopVVIkrbrocAD1Bhxh2XBRDpT5GxxQb09hJnSRGox30Fe3LKFNUMa74kpZM1wKgJ+gQw46LYgjVVDulU/bKwphiaaUnNEGMRmv0Fa7Yp3ynlS6oYLoWAN5jESEQOnHFCyosaSmttH0q+HZtdw4GB9C9ggoxxYoqTmrSdC0AvEeABkLKidGcPwx4Lq74JV2SlFOOfSSB4OGRXNjxWBaS7GPAmcWBFugrOpBXPqssCwqB4KFDDDsuigDaQV/RmayyeeXjildU4R4VCAw6xLDjogigHfQVHbMXFKaUKqlkuhYA3mAONAAAPVRSKaaYfaSR6VoAeIMRhbBjVAlAO+grulFVNamkpIIKaaVNlwOgW4xAAwDQWwkl7A2hM8pUVTVdDoBuEaABAOi5tNL2lpEZZex9bwAMrg+bLgAAgFCY0lRNtYQSbMcBDDrmtIUd8xoBAABcITwBAAAALjAHGgAAAHCBAA0AAAC4QIAGAAAAXCBAAwAAAC4QoAEAAAAXCNAAAACACwRoAMDWIpGI6RIAwC8I0GHHRRFAOzg0AAAcHKQCAAAAuMAINAAAAOACARoAAABwgQANAAAAuECABgAAAFwgQAMAAAAuEKABAAAAFwjQAAAAgAsEaAAAAMAFAjQAAADgAgEaAAAAcIEADQAAALhAgAYAAABcIEADAAAALhCgAQAAABcI0AAAAIALBGgAAADABQI0AAAA4AIBGgAAAHCBAA0AAAC4QIAGAAAAXCBAAwAAAC4QoAEAAAAXCNAAAACACwRoAAAAwAUCNAAAAOACARoAAABwgQANAAAAuECABgAAAFwgQAMAAAAuEKABAAAAFwjQAAAAgAsEaAAAAMAFAjQAAADgAgEaAAAAcIEADQAAALhAgAYAAABcIEADAAAALhCgAQAAABcI0AAAAIALBGgAAADABQI0AAAA4AIBGgAAAHCBAA0AAAC4QIAGAAAAXCBAAwCAD4hEIqZLAHyNAA0AAAC4QIAG0BZGpAAAsHkfoLnKAgAAIMAYgQYAAABc+LDpAgAAAIx578IHnpxvO7ZuqhIMEEagAQBASDWk56bvABsRoAEAQBhtlpXJ0NgSARoAAABwgQANAAAAuECABgAAAFwgQAMAAAAuEKABAEAYbbZjHTvZYUsEaAAAEFIbszLpGe2IrK97/IcSiXj/mQCMo2kD4UF7B1pjBBoAAACB8stfXn/55Z8eOjQdiZw5dGj65Zd/urp6w8PPZwQaQFto2kB40N4x0Obnl++990LDm6Oju7/73QO3336rJ1/BCLQBvb4rCob5+eVI5Ewkcub8+bbIAHkAABrTSURBVDdN1wKgOdopAL+5fHlpY3qWNDOz+M1vznr1LQTofpufX/7MZ545fLg4M7MoaWZm8fDh4te+9sovf3nddGk+Uv/Xf9ttHzNbDICmaKcA/GZx0XrooYv269HR3Ssrp9bXvz09nbbfmZlZnJ9f9uSLCNB91Z+7okF3/vybzl+/pHj84waLAdAU7RSAD9mjk7YXXzz0sR0fkvQv/sX/7Lz5xhu/8uSLCND949Vd0fz8sq+elnpYz+KidejQ9KlT5fo3//RPo558OABP0E4BNFhdvfHyyz/9+tdfted0PfHE5fog2zeLi5bTNZ07l9qx45aoopJuvfUjzu809F0d+7Ann4J2tHNXtHfvrhafMD+//O///VvPP1+RdPLkvT2rtF3t1BOJnLFfrK9/u8VHLS5aMzOLTf+sd++OdV0pgFZopwA6tnHF3tNPz0k6fjx55swDO3bc0vo/d/qfLbXuoCS9/vovnNd/8RefbvNjO0OA7pONd0X264a7oqYxdHX1xg9/+M4LL1Q7vp9bXb1x+fLS66//wg67p08Pf/GLu0ZHd3f8aV3Ws/ED77jju03/6fTpYU++AvAPb9tj39BOAWy0uGg1nZsqye7innvuYN+KGRubcV63HpHsHgG6Tzq7K7IvtIcPF7v56i5vDT2vZ6PLl5fsF6Ojux97LCHp0KFp+53PfW6Ht98FmOWfoRq3aKcANnIGB0+fHv7Wt+752I4P/eaX//Wb35y1h9ief77yla98oddZ1lY/D/b06eE1rdnzNyTV79Pg1WgFAbpP3N4Vbfao9PjxpKu/Ra9uDb2qp6l33vn99HT67rs/ZT8Ffvnlnzr/dMst/2M3nwz4iq+GatyinQJoMDOz6DyL/ta37rGHAG6/PXruXMp5f8vpqV7d7f/mN39wXn/xi7uc9CzpP//n3zuv778/7snXEaD7wdVd0fz88quvLtqDUvWmp9MPPjj0sR0fqv+b2FL3t4be1tNUw8SVd965+Yd+zz231f+/Cxho/hmq6QDtFECD2dm/t1/k86P2yi5b/aKIzaanem5x0XJe3377n9T/U3229mrBBgG6H1zdFTUMUDlDvB1cnzy5NXRbz2aPmBve3+yOc01r9ePcrmaYAH7mq6Ea2ikQPO9diNT/uO1YD8+SXNPa71f/m/3oTNIXv/hPOr6F9mRm2prWXn+95vy4bdsHivm7v7s5jvmJT3zUZYHNsY1dP3R8VzQ9nX7uuYP2BbWDP802bw3b/8Au62nH71f/m/P6+PHkmtZ68S1A/3neHg2inQJ+05Cem77joaiiP//5e86PDTvB9/985aii9RsbfOL2D8wrq3+K7tVTPkage66bu6LDh4uvv/6Lv/zLPXfeucPVGI+Ht4ae1NO+X//65pD83Xd/iofCCAC/DdV0j3YK+MpmWfm9C5HejUP/5Cerzuv6LcXWtPa73/3R+fHcuVSPCmihvlOqn0abz4969RUE6J5ze1f05pvH3njjV85A1PPPV+zrbj4/ev/9n2lz7k5U0bd+fvMvpptbQ7f1NFy229xf1vHLX/4X5/UnP/k/tV8n4Fsetkev0E4BdOlHP/q187p+VmdU0ZmZHzv/tHt3rPUc1J7e7euDQf/zn/dsyyCmcPTblndFe/fu+sbJu1ZWTjXcJ42Nzdxxx3e//vVX2zyw0KtbQ6/qacea1uqnu9xzz21efTJglp+HatyinQJY05rzVE3Sb375X53X8/PL9bPR7rnntj48pFrTWn3/6QxMrK7ecLZBO3486eEqbUagTaq/pt5//2ecW7SootEd+vJjf/4v/+We73//H+r3XbYHgEdHd7/yyuHWH+7VraFX9bQjqmj9dBcgMAZlqKYdtFMAv1r8Q/2PL7xQPXXqf7n11o/Mzy9PTNx8tJ7Pj/ZnkXFU0fpDNi5fXnrkkTtXV2985zs/dN48c+YBD/cLiqyvezw5JhLx/jMH2prW/u35Hzt3Yysrp+w/ptXVGzt3nrPfPH482Xr/15mZxYaT/1pfR9e09tHI/+X8+ItfnLj99lvt1w3nODj1uNJ+Pa4eDdf//8SrUA6v0LQ71uv22D3aKRrQ3gdLi/WCPZoDffny0kMPXWz9O6dPD+fO3tvPNRKHDk1vdkby9HT6kUfu9PC7mMLRcxvviiQ13BX963+9t/WH2Fept9/+5vHjSfud1sveN94aXr/+R0le3Rq6radN9c+y778/ztJ+BEOv22Of0U4Bv9ksJfduBeE//uPNLTiarsw7fXr47NkH+7zC+MUXDzU9aPCVVw57m57FCHTftLgreuWVw+0cLGk/d1jT2lvz1htv/Kr1tuR9uDV0VU+bZmYWncOB//ZvH33wwaHuPxNeoWl3zJ9DNR2jnYYB7X0Q9XMf6K9//VVnDvTKyilJ3/ve2/Zs49Onhw8e3G3kTCh7y6PLl5cuXfrJzMzi6OjuI0c+/+CDQ70Ym2AOdJ+8+OKhr33tlY0Zus30rP+++jCq6N69u7b8u2y4Naw/SNxm3xq2872e1NOm+pVJu3b9SYvfBAZIH9pjP9FOAX/qaWJuUL+C0D6T+MuP/fljj93dtwKaspdsPfLInV965M/sMT77f/fiu5jC0Scf2/GhF188ND2dtuPy6Oju6en0ysqpNtOzW/Urlr70pTvq99A4fXr4zTeP+fNqXb8yaefOW3g0jGAY0Pa4GdopEHL1d9HnzqWcATVzFTWqL6lHhTGFo9+c+yHnf/fiW+pPW/jD+v/R0+/y1qDUGUI07Y4NbnvczKDXjy3R3tFC/bS09h+kBwwj0P3Wh7si/98atjAodQJtGuj2uJlBrx9Ax9a0Vj8tbeMhyiFBgA6g5eWbh4S1eXIhgB6hPQIIkqii9dPSPvvZbQaLMYhFhEHDrSHgH7RHAMHz3HMH/5/n3t+iLrSrIBiBDhpuDQH/oD0CCKT641TNVmIKiwiDyVniw1ofeIWm3THaIwYO7R1ojQANoC00bSA8aO9Aa0zhAAAAAFwgQAMAAAAuEKABAAAAFwjQAAAAgAsEaAAAAMAFAjQAAADgAgEaAAAAcIEADQAAALhAgAYAAABcIEADAAAALhCgAQAAABcI0AAAAIALBGgAAADABQI0AAAA4AIBGgAAAHCBAA0AAAC4QIAGAAAAXCBAAwAAAC4QoAEAAAAXCNAAAACACwRoAAAAwAUCNAAAAOACARoAAABwgQANAAAAuECABgAAAFwgQAMAAAAufNh0AQAAAE28dyFS/+O2Y+umKgEaMAINAAB8pyE9N30HMIUADQAA/GWzrEyGhk8QoAEAAAAXCNAAAACACywiBAAACAXWZXqFEWgAAIDgY12mhwjQaIsly3QJAICw2GxklBHTjrEu01sEaLRlRCM55UxXAQAIi41ZmfQM/4isr3v85xiJeP+ZMCupZFXVuOILWogqarocmEHTBsKD9h48LUaauTPpACPQ2EJOuaqqMcXmNU96BgAAIECjlbM6O6lJSRVVdmqn6XIAAADMI0BjU3nln9STkkoqxRU3XQ4AAOgQ6zK9RYBGc0UVs8pKKqiQUsp0OQAAoCusy/QQiwjRxIIW7tN9lqwJTYxr3HQ58AWaNhAetHegNQI0GtVUSyppyRrT2JSmTJcDv6BpA+FBewdaI0DjAyxZSSVrqqWUKqlkuhz4CE0bCA/aO9Aac6BxkyVrRCM11RJKkJ4BAACaIkDjpqyy9oEppGcAAIDNEKDxvqyyRRVjilVUiSlmuhwAAACfIkBDkiY1mVdeUkkl0jMAAEALBGgor3xOOUkllRJKmC4HAADA19iFI+yu6uqwhiUVVEgrbboc+BdNGwgP2jvQGiPQoVZV1T5lcEITpGcAAIB2MAIdXpasO3SHJSutdEEF0+XA72jaQHj0or2/dyFS/yOHSGOgMQIdUitauUt3WbIO6ADpGQDQUw3puek7wABhBDqkkkpWVU0oUVHFdC0YDDRtIDy8be8tsjLj0BhQjECHUUYZ+8AU0jMAAIBbBOjQOaETRRWjil7RFdO1AAAADB4CdLic1dln9aykOc3FFTddDgAAwOAhQIdIUcUn9aQ4MAUAAKALBOiwKKucUUZSQQV772cAAPpgs5WCrCDE4CJAh8KCFo7oiKRxjXNgCgCgzzZmZdIzBhrb2AVfTbWkkhyYgi7RtIHwoL0DrRGgA86SlVSyplpKqZJKpsvBAKNpA+FBewdaYwpHkK1p7YiO1FRLKEF6BgAA8AQBOsiO6mhZ5ZhipGcAAACvEKADK6tsUcWYYhVVYoqZLgdA0JRVrqlmugoAMIAAHUyTmswrL6mkEgemAPCKJauoYkaZ7do+ohG7nwGAsPmw6QLgvaKKOeXEgSkA2vPehUj9jxv3F6upNq3p1/RaWWXnzbji3J8DCCd24TBvy0uXK1VVk0pKmtLUmMa6qgyoQ9MOqoYuyGZ3RFd1dVaz05qun6qRUuoBPTCmMeaGBRjtHWiNAG1Yi0tXB5z0PK7xCU14VRXb3UM07YBq2gXZbjsWXdOa/TqmmB2ahzUcVbRf1cEY2jvQGgHapBaXrg4ya021YQ0va/mojl7URW+rIkODph1ILXqhPz2muOKHdTitNJPBwob2DrTGHOiAsGQd1MFlLaeU8jw92++ToYFQeVfv7tRO01UAgB+xC0dAHNGRBS1wYAqALdk7aWSV/ag+2uLXSM8AsBlGoIMgowwHpgBorelOGgCADhCgB94JnSiqGFWUA1OAsGlnvW9V1aKKTXfS+Kq+uu3YTpY9AIBbLCI0rMtL16Qm7S2fK6p4ssrH23WNCBKatt+06D0sWa/pNXu82ZJl/5O9k8ZX9dX92t+wkwYb76AB7R1ojQBtXseXrrLKIxqRVFIppVSP6nFbFYKKpu0rLe51HzmWajju5LAOH9CBfdrXl9IQBLR3oDUC9KBy0vMzeuZxPe7thzMchY1o2r7Sevs5SSmlDujAl/VlZnahA7R3oDXmQA+kBS0c0RFJ4xr3PD2LxAwMsoIKD+gBcjMA9A7b2A2eFa3cp/ssWWmluzluEMDAqamWV95++rSZtNKkZwDoKUagB8ya1g7qoCUrpVRBBdPlAPBG63lT9k4aZZWrqva3LgBAE8yBHiSWrCM6UlY5rviSlkyXg3ChafdO0wnNHzn2h1nNllUuqtiwk8ZhHX5AD3zowvaN/xXzr+AJ2jvQGgF6kGSUKaoYU+xtvc0jWvQZTbtHtlwOKCmm2JjGHtADDfvtsN4XPUJ7B1pjCsfAyClnp2cOTAFCYp/2HdCBwzocV7zpL5CYAcAIAvRgyCs/qUlJJZU2u5QCGCxrWruiK/du/gtzmutfNQCAthGgB0BRxayykgoqeHLcIACDaqrZM5vt405+a7oeAIBbBGi/q6qaUUbShCbSSpsuB0CHmu6ksU/7pKsGqwIAdIBFhL5WVTWppKRxjbPlM8yiaXfAkvWaXmvYSUNSWml7Jw17PUPTdYTMb4ZBtHegNQK0f1mykkrWVDuqoxd10XQ5CDuadvssWUUViyrOaW5Na/abm+2kYWM/DfgK7R1ojQDtU5asEY1UVU0pVVLJdDkATXtrm03SaL2TBuBDtHegNQK0T41oxD4whU3r4BM07abWtDanOXu8uf64k3t0z1f1VWeSBjBYaO9Aaywi9KOMMqRnwM9WtPI9fc/ZScMWVzylVFrpppM0AACBQYD2nUlNFlWUdEVXSM+Ar1RVndXs9/S9+kkaCSXsRYFM0gCAkCBA+0te+ZxykiqqcDEG/MCSZU9ubr2TBgAgPAjQPlJWmQNTAJ+wd9Kwd6Bz3tylXQd0gEkaABByBGi/KKs8ohFxYApgFDtpAAC2xC4cvlBTLamkJYsDU+BbwW7aZZVnNftX+itnkkZU0WEN2zs3M0kDYRPs9g50jwBt3opW9mpvTbW00gUVTJcDNBe8pt10J43Wx50AIRG89g54iwBt2JrWhjVcVTWhREUV0+UAmwpM017Qgp2bG3bSSCk1pjEmaQAKUHsHeoQ50CZZso7oSFVVe8tn0+UAQeasCGQnDQBAlwjQJuWUK6scU2xe86ZrAQJoRStXdfXf6d/NatZ5M6ZYWml20gDgW+9diNT/uO0YTwN8hykcxkxqMqdcTDG2fMZAGKCmXVMtr/yc5q7qqvMmx50A7Rug9h48DenZRob2GwK0GXnl7S2fX9WrB3TAdDnA1vzftGc1e1VX88o3TNKwj9dmkgbQPv+396Bqmp5tZGhfYQqHAUUVnQNTSM9AN1a0Ulb5r/RXc5pb05r9ZkyxL+vLB3SASRoAgF4gQPfbghYyyogDU4Au1FR7SS+VVd44SSOlFAd5AgB6igDdVzXV7tN9ksY1Pq5x0+UAA6ao4pzm6o87EZM0AAB9R4DuH0vWfu23ZKWU4rhBoE2WrNf02rSmiyo6b7KTBgDAIBYR9okla0QjHJiCweVt095ykyZ7J42qqvXHBDJJA+gPLuUGsQvHQCBA98mIRsoq2wem8KAZg8jDpt3i8lBW+TW91rCThj1Dg0kaQN9wKTeLfaD9jwDdD1ll88rv0q4f68ckAAwor5p2i02a/vTYzddM0gAM4lIOtMYc6J6b1GReeUkllUjPQGsJJezxZiZpAAB8iwDdW3nlc8pJKqm0R3tMlwP42rt6d6d2mq4CAIAtEKB7qKyyc2AKj6ERbK1n7NXvpPHbzT+E9AwAGAgE6F6pqjqiEXFgCkJg47Tm9y5Eth1br6k2rWn7hG0jhQEA0AssIuyJmmrDGl7W8pjGpjRluhzAA5s17TYXBdbvpMEmTYDPcSkHWmME2nsrWtmv/ctaTilFekaY2Ttp2NG5/v1tx9bZpAkAMLgI0B5b09pBHaypllCipJLpcoDeqql26+b/ek3XNvsnEjMAYHB9yHQBQZNRpqqqfWCK6VqAXimrnFNuSENDGjJdCwAA/RbMEWhTT4dP6MSsZmOKzWu+P98I9FNRxWlNv6bXnGMCY4qp7shAAADCIICLCE2tTzqrs0/qSUkVVbY8A4IJoBgU9k4ar+m1ssrOm3HFxzSWUsr+U2dRIBAwxi/lgM8FLUC32BCgp5fzvPL2ls8llbbc8pm0Af8rq2zv3FxTzXkzpdQDemBMYxvP1OSeEAgSAjTQGgHaA2WV7S2fCypsueWzqYgPbMk57qRhkoYdmkciI1xQgZAgQAOtBXMOdD8taOGIjogDUzCwNpukcViH00pvOR8JAICwIUB3pabafbrPkpVWelzjpssB3JnUZF75hkkaznEnBgsDAMDPCNCds2Tt135LVkqpggqmywE6UVPNnqRhjzebLgcAgAEQtDnQ6tcSvTWtDWu4qmpCCVdbPjMHGv5RU82S1eYkDeNNG0Df0N6B1gIYoNWXDQEyyhRVtA9Mcfuwm104MIj80LQB9AftHWgtmAG617LK5pWPKfa23u5sqih7fmHghKFpA7DR3oHWCNCuTWoyp5zaOzAFCIzAN20ADto70NqHTBcwYPLK2+m5pBLpGQAAIIQYgXahqmpSSbV3YAoQMAFu2gAa0N6B1hiBbpeTnjkwBQAAIMwYgW5LTbX92l9TLa00Wz4jnALZtAE0RXsHWiNAb21FK3u1t6ZaSqmSSqbLAcwIXtMGsBnaO9AaUzi29qgeramWUIL0DAAAAAL0FjLKlFWOK056BgAAgKQPmy7A107oRFFFSVd0pbMDUwAAgN9wnBm6xAj0ps7q7LN6VtLP9LO44qbLAQAAHmhIz03fAVpjEWFzs5o9qIOSSiqllDJdDmBeMJo2gHYEuL23yMqMQ6N9TOFooqyynZ4v6iLpGQAAoKcGblINUzgaLWjhiI5IGtf4UR01XQ4AAECQDeKkGgL0B9RUu0/3WbLSSk9ownQ5AAAAQbZZVvZ5hiZAf8B+7bdkpZTiuEEAAAA0RYB+nyVrRCMcmAIAQIBtNrnW/5Nu4SsE6PdllS2rHFPsVb1quhYAANArG7My6RlusQuHJGWVLaoYU6yiyk7tNF0OAADoIRIzusQItPLK55WXVFKJA1MAAAD6ZkAn1YQ9QBdVzCorqaRSQgnT5QAAAITLIE6qCfVJhFVVk0pKmtDEuMZNlwP42gA1bQBdor0DrYV3BNpJz+MaJz0DAACgTSEdgbZk3aW7lrV8VEcv6qLpcoABMBBNG4AnaO9Aa2Ecgba3fF7Wckop0jMAAABcCeMI9IhGyirHFV/SkulagIHh/6YNwCu0d6C10I1AZ5SxD0ypqGK6FgAAAAyecAXonHJFFaOKVlSJKWa6HAAAAAyeEAXovPKTmpQ0pzkOTAEAAEBnwhKgZzVrH5hSUIEDUwAAANCxUATossoHdVDShCbSSpsuBwAAAAMs+AF6QQtHdEQcmAIAAAAvBHwbuxWt7NXemmpppQsqmC4HGGC+atoAeor2DrQW5BHoNa0d1MGaaimlSM8AAADwxIdNF9ArlqwjOlJVNa74JV0yXQ4AAP0TiUSMfwIwKDp43hLYKRwZZYoqxhR7W2+z5TPQPZ80bQB9QHsHWgvmCPRZnbXTMwemAA5GpID2ER8BtNDkFnPgr5FpvT/h+V5p3nAtCLzwXGUZkQLCg/YOtBa0KRxllUc0IqmgAls+Ax7iggqEB+0daC1Qu3BUVbXTMwemAAAAoEeCMwJtydqu7ZLGNT6hif4XAAQbI1JAeNDegdYCMgJtyUoqKSmtNOkZAAAAvROQEeikklVVE0pUVOnzVwMhwYgUEB60d6C1IGxjN6IR+8CUkkpNf+G9Cx/YV2TbMToFAAAAdGjgp3BklS2r3GLL54b03PQdAAAAoE2DHaAnNZlX3lV6bv0+AAAA0NoAB+i88jnlJF3SpbjipssBAABAKAxqgC6rnFVWUkGFlFKmywEAAEBYDGSA5sAUAAAAmDJ4AdqSZafncY2Pa9x0OQAAAAiXAdsH2j4wpaZaWumCCu38J03XC7KTHeAW+8IC4UF7B1obsBHomGJjGkso0WZ6VrOsTHoGAABAxwZsBBqAKTRtIDxo70BrAzYCDQAAeo30DLRGgAYAAABcIEADaAsjUgAA2JjkBAAAALjACDQAAADgAgEaAAAAcIEADQAAALhAgAYAAABcIEADAIAPiEQipksAfI1dOAAAAAAXGIEG0BZGpAAAsHkfoLnKAoHE0yoAAGxM4QAAAABcYAoHAAAA4AIBGgAAAHCBAA0AAAC48P8DedtntqC0ypIAAAAASUVORK5CYII="}}},{"cell_type":"markdown","source":"# Let's see the Data","metadata":{}},{"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport os\nimport warnings","metadata":{"execution":{"iopub.status.busy":"2022-09-06T20:37:12.925198Z","iopub.execute_input":"2022-09-06T20:37:12.925954Z","iopub.status.idle":"2022-09-06T20:37:12.955610Z","shell.execute_reply.started":"2022-09-06T20:37:12.925859Z","shell.execute_reply":"2022-09-06T20:37:12.954690Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"metadata = pd.read_csv('../input/open-problems-multimodal/metadata.csv').set_index('cell_id')\nevaluation_ids = pd.read_csv('../input/open-problems-multimodal/evaluation_ids.csv').set_index('row_id')","metadata":{"execution":{"iopub.status.busy":"2022-09-06T20:37:12.957224Z","iopub.execute_input":"2022-09-06T20:37:12.957726Z","iopub.status.idle":"2022-09-06T20:38:11.995626Z","shell.execute_reply.started":"2022-09-06T20:37:12.957695Z","shell.execute_reply":"2022-09-06T20:38:11.994437Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"metadata.head()","metadata":{"execution":{"iopub.status.busy":"2022-09-06T20:38:11.996978Z","iopub.execute_input":"2022-09-06T20:38:11.997336Z","iopub.status.idle":"2022-09-06T20:38:12.015285Z","shell.execute_reply.started":"2022-09-06T20:38:11.997304Z","shell.execute_reply":"2022-09-06T20:38:12.014045Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"evaluation_ids.head()","metadata":{"execution":{"iopub.status.busy":"2022-09-06T20:38:37.446769Z","iopub.execute_input":"2022-09-06T20:38:37.447995Z","iopub.status.idle":"2022-09-06T20:38:37.459863Z","shell.execute_reply.started":"2022-09-06T20:38:37.447950Z","shell.execute_reply":"2022-09-06T20:38:37.458628Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# EDA and Visualization ","metadata":{}},{"cell_type":"code","source":"metadata.dtypes","metadata":{"execution":{"iopub.status.busy":"2022-09-06T20:39:03.375954Z","iopub.execute_input":"2022-09-06T20:39:03.376386Z","iopub.status.idle":"2022-09-06T20:39:03.385534Z","shell.execute_reply.started":"2022-09-06T20:39:03.376352Z","shell.execute_reply":"2022-09-06T20:39:03.384189Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"","metadata":{}},{"cell_type":"code","source":"evaluation_ids.dtypes","metadata":{"execution":{"iopub.status.busy":"2022-09-06T20:39:10.460766Z","iopub.execute_input":"2022-09-06T20:39:10.461340Z","iopub.status.idle":"2022-09-06T20:39:10.471594Z","shell.execute_reply.started":"2022-09-06T20:39:10.461287Z","shell.execute_reply":"2022-09-06T20:39:10.470467Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Analysis of missing values\n\nThere are no missing values","metadata":{}},{"cell_type":"code","source":"nan_cols_metadata = metadata.columns[metadata.isna().any()].tolist()\nnan_cols_evaluation_ids = evaluation_ids.columns[evaluation_ids.isna().any()].tolist()\nprint(nan_cols_metadata, nan_cols_evaluation_ids)","metadata":{"execution":{"iopub.status.busy":"2022-09-06T20:39:20.573439Z","iopub.execute_input":"2022-09-06T20:39:20.573841Z","iopub.status.idle":"2022-09-06T20:39:26.470365Z","shell.execute_reply.started":"2022-09-06T20:39:20.573808Z","shell.execute_reply":"2022-09-06T20:39:26.469208Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"fig, axarr = plt.subplots(nrows=1, ncols=4, figsize=(12, 4))\nfor i, col in enumerate([\"day\", \"donor\", \"cell_type\", \"technology\"]):\n    _= metadata[[col]].value_counts().plot.pie(ax=axarr[i], autopct='%1.1f%%', ylabel=col)","metadata":{"execution":{"iopub.status.busy":"2022-09-06T20:41:05.396318Z","iopub.execute_input":"2022-09-06T20:41:05.396730Z","iopub.status.idle":"2022-09-06T20:41:05.925952Z","shell.execute_reply.started":"2022-09-06T20:41:05.396696Z","shell.execute_reply":"2022-09-06T20:41:05.924915Z"},"trusted":true},"execution_count":null,"outputs":[]}]}