{"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":"Published on June 23, 2023. By Marília Prata, MPwolke.","metadata":{}},{"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)\nimport seaborn as sns\nimport matplotlib.pyplot as plt\n\nimport plotly.express as px\nimport plotly.graph_objs as go\n\nimport plotly\nplotly.offline.init_notebook_mode(connected=True)\n\n#Ignore warnings\nimport warnings\nwarnings.filterwarnings('ignore')\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","_kg_hide-input":true,"_kg_hide-output":true,"execution":{"iopub.status.busy":"2023-06-23T21:25:17.414050Z","iopub.execute_input":"2023-06-23T21:25:17.414501Z","iopub.status.idle":"2023-06-23T21:25:19.355931Z","shell.execute_reply.started":"2023-06-23T21:25:17.414466Z","shell.execute_reply":"2023-06-23T21:25:19.354787Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"![image.png](attachment:712320aa-c700-4e22-9638-8cb9574e799f.png)\nhttps://www.kaggle.com/competitions/Raising-Money-to-Fund-an-Organizational-Mission/overview","metadata":{},"attachments":{"712320aa-c700-4e22-9638-8cb9574e799f.png":{"image/png":"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"}}},{"cell_type":"markdown","source":"Only 27 teams, 11 years ago. Let's check some Discussion topics:\n\n#Post-Mortem \n\nTopic by Barrenwuffet (9th place)\n\n\"Anybody do or find anything interesting in this dataset? Or find any good tools for working with large data sets?\"\n\n\"I found it barely manageable given the size.  It also took me awhile to wrap by head around what was in each of the files. Also the database restrictions (1 and 2 but not 3, 1 and 2 and 3, 2 and 3 but not 1, etc) made a really difficult task much harder and considerably less enjoyable.  I ended up having to write 12 large files (and accompanying SQL code) for each model to compensate for this.\"\n\n\"I started out with a ~2% sample of the training data in R but even this was rough.  I tried using the ff package without much luck.  I ended up doing most of the data manipulation using SQL Server 2008 R2 Express and the SSMS which I found to be a bright spot in the whole process as it performed really well given the data size.  I especially appreciated the data import manager which helps with wide data sets.\"\n\n\"My best model ended up just being prior averages for prospectid, zip5, and packageid with linear regression.  I predicted donation amount (not amount2) and response rate using separate models.  I'd then do predictedGift^1.15 * predictedResponseRate for a final prediction.\"\n\n\"I tried to use some of the demographic data but had a hard time as I was using zip5 as the key to get state abbreviations as a factor, but some of the zip codes cross state lines which leads to duplicates and zip9, even when indexed, just took too long.\"\n\n\"I think the contest was a cool idea but would have been much better on just one of the 3 databases.  Without that restriction I would have had more time to explore the demographic and historical data.  The one thing I would have really liked to explore is people's giving before the training period especially as much of the mailings seemed to be political and the test data is sitting within 12 months of a presidential election.\"\n\nhttps://www.kaggle.com/competitions/Raising-Money-to-Fund-an-Organizational-Mission/discussion/2712","metadata":{}},{"cell_type":"code","source":"!unzip -n ../input/Raising-Money-to-Fund-an-Organizational-Mission/training_sample.zip","metadata":{"execution":{"iopub.status.busy":"2023-06-23T21:25:26.570622Z","iopub.execute_input":"2023-06-23T21:25:26.571026Z","iopub.status.idle":"2023-06-23T21:25:34.108945Z","shell.execute_reply.started":"2023-06-23T21:25:26.570995Z","shell.execute_reply":"2023-06-23T21:25:34.107379Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#When will the winner's solution be posted? \n\nBy Sashikanth Dareddy (7th place) - 11 years ago\n\n\"It has been more than a month since this competition has ended, any update on when the winner's solution will be posted to the public forum?\"\n\nAnswer by David Chudzicki - Competition Host - Posted 10 years ago\n\n\"The solution won't be posted. They're generally not, but we do have some open source contests where solutions are posted publicly.\"\n\n\"For some other competitions, you can see this wiki page listing what's available about some past competitions' solutions. Much of what's listed there aren't full solutions, just forum posts where people describe their approach:\"\n\nhttps://www.kaggle.com/wiki/PastSolutions\n\n\"The page is pretty incomplete, so feel free to improve it if you find more listed on competition pages or forums.\"\n\nhttps://www.kaggle.com/competitions/Raising-Money-to-Fund-an-Organizational-Mission/discussion/3049","metadata":{}},{"cell_type":"code","source":"!unzip -n ../input/Raising-Money-to-Fund-an-Organizational-Mission/test.zip","metadata":{"execution":{"iopub.status.busy":"2023-06-23T21:13:09.615281Z","iopub.execute_input":"2023-06-23T21:13:09.615729Z","iopub.status.idle":"2023-06-23T21:13:16.124557Z","shell.execute_reply.started":"2023-06-23T21:13:09.615690Z","shell.execute_reply":"2023-06-23T21:13:16.123548Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#Test csv\n\nThere were many IDs on test file.","metadata":{}},{"cell_type":"code","source":"test = pd.read_csv(\"/kaggle/input/Raising-Money-to-Fund-an-Organizational-Mission/test.csv\", delimiter=',', encoding='ISO-8859-2')\npd.set_option('display.max_columns', None)\ntest.head()","metadata":{"execution":{"iopub.status.busy":"2023-06-23T21:04:22.510956Z","iopub.execute_input":"2023-06-23T21:04:22.511459Z","iopub.status.idle":"2023-06-23T21:04:37.675559Z","shell.execute_reply.started":"2023-06-23T21:04:22.511410Z","shell.execute_reply":"2023-06-23T21:04:37.674344Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#Missing values only on zip4","metadata":{}},{"cell_type":"code","source":"test.isnull().sum()","metadata":{"_kg_hide-output":true,"execution":{"iopub.status.busy":"2023-06-23T21:04:37.677302Z","iopub.execute_input":"2023-06-23T21:04:37.678035Z","iopub.status.idle":"2023-06-23T21:04:44.233967Z","shell.execute_reply.started":"2023-06-23T21:04:37.677988Z","shell.execute_reply":"2023-06-23T21:04:44.232605Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#Where is everybody? Topic by Benoit Plante 10th place- Posted 11 years ago.\n\n\"Where are everybody?\"\nThere is not a lot of competition this time... Good for me ;) just kidding.\n\nhttps://www.kaggle.com/competitions/Raising-Money-to-Fund-an-Organizational-Mission/discussion/2336\n\nAnswer by mal_sch - Posted 11 years ago\n\n\"As I spend a lot of time on this data set and will not produce a single solution, I'd like to comment on this. It's a bit frustrating spending hours and hours on a project and not coming to a solution. However, I shouldn't complain since I didn't succeed because I did not figure out how to calculate effectively on such large amounts of data. At least I learned a lot in this project about big data handling.\"\n\n\"Please consider the following not as a critic but as personal feelings where I was unhappy with the given data and information.\"\n\n\"In the following aspects I wished the documentation were clearer and more precise:\"\n\n\"on the data download site it says the mail and donation dataset are prior to the training dataset. At least in my work this turned out to be false - there are many mails both in the mail and training dataset. This made the reeeeeaaaaally time consuming task of merging mail, donation and training data even harder.\"\nMany variables are saved in both mail and donation datasets. Logically the values should not be different and I would have appreciated having this data only stored in a single file.\"\n\"I found it hard to understand the structure in the data. One example is that each ListId has only one VectorMajor and one VectorMinor and VectorMajor is only more general than VectorMinor. It would have helped to know from the documentation that VectorMajor/VectorMinor are properties of ListId, not from the mail record.\nAll in all I feel I had to do too much time consuming data reading and data merging tasks (which are boring to me) and too little data modelling (far more interesting).\"\n\nAnswer by Steffen - Posted 11 years ago\n\n\"I was thinking the same ...\n\n\"For me it is the fact that I have to download a lot of data (ton of data) and dig through a rather complicated setup. Nothing is as rewarding as creating a first 80/20-submission within the first hours of getting into the competition before diving into the mind numbing 20/80 optimization ;)\"\n\n\"But since I am only a doofus who has not yet achieved a lot on kaggle, I should rather be quiet and let the pros get some work done.\"\n\n\"I want to emphasize that my posts that far do NOT mean that I despise the competition or the compeitition organizer ... I think this whole thing is a very good idea.\"\n\n\"Happy mining to all :)\n\nhttps://www.kaggle.com/competitions/Raising-Money-to-Fund-an-Organizational-Mission/discussion/2336","metadata":{}},{"cell_type":"code","source":"import zipfile\ntraining= zipfile.ZipFile('../input/Raising-Money-to-Fund-an-Organizational-Mission/training_sample.zip')\ntraining.extractall()","metadata":{"execution":{"iopub.status.busy":"2023-06-23T21:27:32.707393Z","iopub.execute_input":"2023-06-23T21:27:32.707964Z","iopub.status.idle":"2023-06-23T21:27:37.737068Z","shell.execute_reply.started":"2023-06-23T21:27:32.707918Z","shell.execute_reply":"2023-06-23T21:27:37.735330Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Load Dataset\nfilename    = 'training_sample.txt'\ntext        = open(filename, encoding='utf-8').read()\ntext        = text.lower()\nprint('corpus length:', len(text))\n\n# Find all the unique characters\nchars        = sorted(list(set(text)))\nchar_indices = dict((c, i) for i, c in enumerate(chars))\nindices_char = dict((i, c) for i, c in enumerate(chars))\nvocab_size   = len(chars)\n\nprint(\"List of unique characters : \\n\", chars)\nprint(\"Number of unique characters : \\n\", vocab_size)\nprint(\"Character to integer mapping : \\n\", char_indices)\nprint (filename[:53])","metadata":{"execution":{"iopub.status.busy":"2023-06-23T21:20:24.928917Z","iopub.execute_input":"2023-06-23T21:20:24.929909Z","iopub.status.idle":"2023-06-23T21:20:42.215046Z","shell.execute_reply.started":"2023-06-23T21:20:24.929875Z","shell.execute_reply":"2023-06-23T21:20:42.213842Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#I couldn't open training_sample since it has allocated too much memory","metadata":{}},{"cell_type":"code","source":"!pip install python-docx","metadata":{"execution":{"iopub.status.busy":"2023-06-23T21:33:49.891294Z","iopub.execute_input":"2023-06-23T21:33:49.892747Z","iopub.status.idle":"2023-06-23T21:34:08.163823Z","shell.execute_reply.started":"2023-06-23T21:33:49.892687Z","shell.execute_reply":"2023-06-23T21:34:08.161937Z"},"_kg_hide-output":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import docx","metadata":{"execution":{"iopub.status.busy":"2023-06-23T21:34:57.599413Z","iopub.execute_input":"2023-06-23T21:34:57.600012Z","iopub.status.idle":"2023-06-23T21:34:58.019445Z","shell.execute_reply.started":"2023-06-23T21:34:57.599959Z","shell.execute_reply":"2023-06-23T21:34:58.017873Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#Reading docx file","metadata":{}},{"cell_type":"code","source":"#Code by Stack Overflow https://stackoverflow.com/questions/29309085/read-docx-files-via-python¶\n#Answered by Zaid.mohammed in Stack Overflow Nov 30 '19 at 12:43\n\ndef main():\n    try:\n        doc = docx.Document('../input//Raising-Money-to-Fund-an-Organizational-Mission/Kaggle FAQ.docx')  # Creating word reader object.\n        data = \"\"\n        fullText = []\n        for para in doc.paragraphs:\n            fullText.append(para.text)\n            data = '\\n'.join(fullText)\n\n        print(data)\n\n    except IOError:\n        print('There was an error opening the file!')\n        return\n\n\nif __name__ == '__main__':\n    main()","metadata":{"execution":{"iopub.status.busy":"2023-06-23T21:36:42.636170Z","iopub.execute_input":"2023-06-23T21:36:42.637359Z","iopub.status.idle":"2023-06-23T21:36:42.682427Z","shell.execute_reply.started":"2023-06-23T21:36:42.637308Z","shell.execute_reply":"2023-06-23T21:36:42.679690Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"That's all for now","metadata":{}}]}