In [ ]:

# from google.colab import files
# uploaded = files.upload()

In [ ]:

# !cp "data.csv" "/content/drive/My Drive/fifa.csv"

In [2]:

!pip install pycaret==2.0

Collecting pycaret==2.0
  Downloading https://files.pythonhosted.org/packages/91/ae/000d825af8f7d9ff86808600f220e7ad57a873987fd6119c87dc4c5b1d91/pycaret-2.0-py3-none-any.whl (255kB)
     |████████████████████████████████| 256kB 3.3MB/s 
Requirement already satisfied: matplotlib in /usr/local/lib/python3.6/dist-packages (from pycaret==2.0) (3.2.2)
Collecting yellowbrick>=1.0.1
  Downloading https://files.pythonhosted.org/packages/13/95/a14e4fdfb8b1c8753bbe74a626e910a98219ef9c87c6763585bbd30d84cf/yellowbrick-1.1-py3-none-any.whl (263kB)
     |████████████████████████████████| 266kB 8.5MB/s 
Requirement already satisfied: joblib in /usr/local/lib/python3.6/dist-packages (from pycaret==2.0) (0.16.0)
Requirement already satisfied: umap-learn in /usr/local/lib/python3.6/dist-packages (from pycaret==2.0) (0.4.6)
Requirement already satisfied: plotly>=4.4.1 in /usr/local/lib/python3.6/dist-packages (from pycaret==2.0) (4.4.1)
Collecting mlflow
  Downloading https://files.pythonhosted.org/packages/00/2f/2529268d85af0a1521b0b7c137b63b731dff4784e1322fb3055403a959fb/mlflow-1.10.0-py3-none-any.whl (12.4MB)
     |████████████████████████████████| 12.4MB 314kB/s 
Collecting datefinder>=0.7.0
  Downloading https://files.pythonhosted.org/packages/0c/4f/29524c9ca35d2ba1a8a3c6c895b90fc92525cf0fe357f747133890953ebe/datefinder-0.7.1-py2.py3-none-any.whl
Requirement already satisfied: seaborn in /usr/local/lib/python3.6/dist-packages (from pycaret==2.0) (0.10.1)
Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.6/dist-packages (from pycaret==2.0) (1.18.5)
Collecting pyod
  Downloading https://files.pythonhosted.org/packages/77/4e/5767edaccbfc227914ca774cb6ca9b628a08cbb59b9b4839296953a63d34/pyod-0.8.1.tar.gz (93kB)
     |████████████████████████████████| 102kB 9.4MB/s 
Requirement already satisfied: textblob in /usr/local/lib/python3.6/dist-packages (from pycaret==2.0) (0.15.3)
Requirement already satisfied: ipywidgets in /usr/local/lib/python3.6/dist-packages (from pycaret==2.0) (7.5.1)
Collecting pandas-profiling>=2.3.0
  Downloading https://files.pythonhosted.org/packages/b9/94/ef8ef4517540d13406fcc0b8adfd75336e014242c69bd4162ab46931f36a/pandas_profiling-2.8.0-py2.py3-none-any.whl (259kB)
     |████████████████████████████████| 266kB 41.5MB/s 
Requirement already satisfied: imbalanced-learn in /usr/local/lib/python3.6/dist-packages (from pycaret==2.0) (0.4.3)
Requirement already satisfied: spacy in /usr/local/lib/python3.6/dist-packages (from pycaret==2.0) (2.2.4)
Collecting scikit-learn>=0.23
  Downloading https://files.pythonhosted.org/packages/5c/a1/273def87037a7fb010512bbc5901c31cfddfca8080bc63b42b26e3cc55b3/scikit_learn-0.23.2-cp36-cp36m-manylinux1_x86_64.whl (6.8MB)
     |████████████████████████████████| 6.8MB 47.1MB/s 
Collecting lightgbm>=2.3.1
  Downloading https://files.pythonhosted.org/packages/0b/9d/ddcb2f43aca194987f1a99e27edf41cf9bc39ea750c3371c2a62698c509a/lightgbm-2.3.1-py2.py3-none-manylinux1_x86_64.whl (1.2MB)
     |████████████████████████████████| 1.2MB 40.7MB/s 
Requirement already satisfied: pandas in /usr/local/lib/python3.6/dist-packages (from pycaret==2.0) (1.0.5)
Requirement already satisfied: cufflinks>=0.17.0 in /usr/local/lib/python3.6/dist-packages (from pycaret==2.0) (0.17.3)
Requirement already satisfied: xgboost>=0.90 in /usr/local/lib/python3.6/dist-packages (from pycaret==2.0) (0.90)
Collecting DateTime>=4.3
  Downloading https://files.pythonhosted.org/packages/73/22/a5297f3a1f92468cc737f8ce7ba6e5f245fcfafeae810ba37bd1039ea01c/DateTime-4.3-py2.py3-none-any.whl (60kB)
     |████████████████████████████████| 61kB 6.7MB/s 
Requirement already satisfied: IPython in /usr/local/lib/python3.6/dist-packages (from pycaret==2.0) (5.5.0)
Requirement already satisfied: gensim in /usr/local/lib/python3.6/dist-packages (from pycaret==2.0) (3.6.0)
Requirement already satisfied: wordcloud in /usr/local/lib/python3.6/dist-packages (from pycaret==2.0) (1.5.0)
Collecting pyLDAvis
  Downloading https://files.pythonhosted.org/packages/a5/3a/af82e070a8a96e13217c8f362f9a73e82d61ac8fff3a2561946a97f96266/pyLDAvis-2.1.2.tar.gz (1.6MB)
     |████████████████████████████████| 1.6MB 37.7MB/s 
Collecting kmodes>=0.10.1
  Downloading https://files.pythonhosted.org/packages/b2/55/d8ec1ae1f7e1e202a8a4184c6852a3ee993b202b0459672c699d0ac18fc8/kmodes-0.10.2-py2.py3-none-any.whl
Requirement already satisfied: mlxtend in /usr/local/lib/python3.6/dist-packages (from pycaret==2.0) (0.14.0)
Requirement already satisfied: nltk in /usr/local/lib/python3.6/dist-packages (from pycaret==2.0) (3.2.5)
Collecting catboost
  Downloading https://files.pythonhosted.org/packages/96/6c/6608210b29649267de52001b09e369777ee2a5cfe1c71fa75eba82a4f2dc/catboost-0.24-cp36-none-manylinux1_x86_64.whl (65.9MB)
     |████████████████████████████████| 65.9MB 52kB/s 
Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.6/dist-packages (from matplotlib->pycaret==2.0) (0.10.0)
Requirement already satisfied: python-dateutil>=2.1 in /usr/local/lib/python3.6/dist-packages (from matplotlib->pycaret==2.0) (2.8.1)
Requirement already satisfied: pyparsing!=2.0.4,!=2.1.2,!=2.1.6,>=2.0.1 in /usr/local/lib/python3.6/dist-packages (from matplotlib->pycaret==2.0) (2.4.7)
Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.6/dist-packages (from matplotlib->pycaret==2.0) (1.2.0)
Requirement already satisfied: scipy>=1.0.0 in /usr/local/lib/python3.6/dist-packages (from yellowbrick>=1.0.1->pycaret==2.0) (1.4.1)
Requirement already satisfied: numba!=0.47,>=0.46 in /usr/local/lib/python3.6/dist-packages (from umap-learn->pycaret==2.0) (0.48.0)
Requirement already satisfied: six in /usr/local/lib/python3.6/dist-packages (from plotly>=4.4.1->pycaret==2.0) (1.15.0)
Requirement already satisfied: retrying>=1.3.3 in /usr/local/lib/python3.6/dist-packages (from plotly>=4.4.1->pycaret==2.0) (1.3.3)
Requirement already satisfied: protobuf>=3.6.0 in /usr/local/lib/python3.6/dist-packages (from mlflow->pycaret==2.0) (3.12.4)
Collecting gunicorn; platform_system != "Windows"
  Downloading https://files.pythonhosted.org/packages/69/ca/926f7cd3a2014b16870086b2d0fdc84a9e49473c68a8dff8b57f7c156f43/gunicorn-20.0.4-py2.py3-none-any.whl (77kB)
     |████████████████████████████████| 81kB 8.8MB/s 
Requirement already satisfied: pyyaml in /usr/local/lib/python3.6/dist-packages (from mlflow->pycaret==2.0) (3.13)
Requirement already satisfied: cloudpickle in /usr/local/lib/python3.6/dist-packages (from mlflow->pycaret==2.0) (1.3.0)
Collecting databricks-cli>=0.8.7
  Downloading https://files.pythonhosted.org/packages/1e/57/5c2d6b83cb8753d12f548e89f91037632baa8289677c1b2ab2adf14bf6b2/databricks-cli-0.11.0.tar.gz (49kB)
     |████████████████████████████████| 51kB 6.2MB/s 
Collecting alembic
  Downloading https://files.pythonhosted.org/packages/60/1e/cabc75a189de0fbb2841d0975243e59bde8b7822bacbb95008ac6fe9ad47/alembic-1.4.2.tar.gz (1.1MB)
     |████████████████████████████████| 1.1MB 42.6MB/s 
  Installing build dependencies ... done
  Getting requirements to build wheel ... done
    Preparing wheel metadata ... done
Requirement already satisfied: entrypoints in /usr/local/lib/python3.6/dist-packages (from mlflow->pycaret==2.0) (0.3)
Requirement already satisfied: sqlparse in /usr/local/lib/python3.6/dist-packages (from mlflow->pycaret==2.0) (0.3.1)
Collecting gitpython>=2.1.0
  Downloading https://files.pythonhosted.org/packages/f9/1e/a45320cab182bf1c8656107b3d4c042e659742822fc6bff150d769a984dd/GitPython-3.1.7-py3-none-any.whl (158kB)
     |████████████████████████████████| 163kB 32.3MB/s 
Collecting azure-storage-blob>=12.0
  Downloading https://files.pythonhosted.org/packages/6d/3d/31614573e8a197db12d8ab47a7fd813f15bd4a4b5c64e85d23b865de5b9b/azure_storage_blob-12.3.2-py2.py3-none-any.whl (280kB)
     |████████████████████████████████| 286kB 46.6MB/s 
Collecting gorilla
  Downloading https://files.pythonhosted.org/packages/e3/56/5a683944cbfc77e429c6f03c636ca50504a785f60ffae91ddd7f5f7bb520/gorilla-0.3.0-py2.py3-none-any.whl
Collecting prometheus-flask-exporter
  Downloading https://files.pythonhosted.org/packages/84/b0/7549899a75e7ef0be5f8969094d0709e5dcc51dc21d58cc86b8d69441dce/prometheus_flask_exporter-0.15.4.tar.gz
Collecting querystring-parser
  Downloading https://files.pythonhosted.org/packages/4a/fa/f54f5662e0eababf0c49e92fd94bf178888562c0e7b677c8941bbbcd1bd6/querystring_parser-1.2.4.tar.gz
Requirement already satisfied: Flask in /usr/local/lib/python3.6/dist-packages (from mlflow->pycaret==2.0) (1.1.2)
Requirement already satisfied: requests>=2.17.3 in /usr/local/lib/python3.6/dist-packages (from mlflow->pycaret==2.0) (2.23.0)
Collecting sqlalchemy<=1.3.13
  Downloading https://files.pythonhosted.org/packages/af/47/35edeb0f86c0b44934c05d961c893e223ef27e79e1f53b5e6f14820ff553/SQLAlchemy-1.3.13.tar.gz (6.0MB)
     |████████████████████████████████| 6.0MB 40.7MB/s 
Requirement already satisfied: click>=7.0 in /usr/local/lib/python3.6/dist-packages (from mlflow->pycaret==2.0) (7.1.2)
Collecting docker>=4.0.0
  Downloading https://files.pythonhosted.org/packages/3c/15/7a2f095a3b8b0fff9a0a5f56bd941e05fa958d4ca31105541001a5f7d3eb/docker-4.2.2-py2.py3-none-any.whl (144kB)
     |████████████████████████████████| 153kB 45.0MB/s 
Requirement already satisfied: pytz in /usr/local/lib/python3.6/dist-packages (from datefinder>=0.7.0->pycaret==2.0) (2018.9)
Requirement already satisfied: regex>=2017.02.08 in /usr/local/lib/python3.6/dist-packages (from datefinder>=0.7.0->pycaret==2.0) (2019.12.20)
Collecting combo
  Downloading https://files.pythonhosted.org/packages/0a/2a/61b6ac584e75d8df16dc27962aa5fe99d76b09da5b6710e83d4862c84001/combo-0.1.1.tar.gz
Collecting suod
  Downloading https://files.pythonhosted.org/packages/a1/87/9170cabe1b5e10a7d095c0e28f2e30e7c1886a13f063de85d3cfacc06f4b/suod-0.0.4.tar.gz (2.1MB)
     |████████████████████████████████| 2.1MB 43.7MB/s 
Requirement already satisfied: traitlets>=4.3.1 in /usr/local/lib/python3.6/dist-packages (from ipywidgets->pycaret==2.0) (4.3.3)
Requirement already satisfied: ipykernel>=4.5.1 in /usr/local/lib/python3.6/dist-packages (from ipywidgets->pycaret==2.0) (4.10.1)
Requirement already satisfied: widgetsnbextension~=3.5.0 in /usr/local/lib/python3.6/dist-packages (from ipywidgets->pycaret==2.0) (3.5.1)
Requirement already satisfied: nbformat>=4.2.0 in /usr/local/lib/python3.6/dist-packages (from ipywidgets->pycaret==2.0) (5.0.7)
Collecting htmlmin>=0.1.12
  Downloading https://files.pythonhosted.org/packages/b3/e7/fcd59e12169de19f0131ff2812077f964c6b960e7c09804d30a7bf2ab461/htmlmin-0.1.12.tar.gz
Requirement already satisfied: missingno>=0.4.2 in /usr/local/lib/python3.6/dist-packages (from pandas-profiling>=2.3.0->pycaret==2.0) (0.4.2)
Collecting confuse>=1.0.0
  Downloading https://files.pythonhosted.org/packages/b5/6d/bedc0d1068bd244cee05843313cbec6cebb9f01f925538269bababc6d887/confuse-1.3.0-py2.py3-none-any.whl (64kB)
     |████████████████████████████████| 71kB 8.1MB/s 
Requirement already satisfied: jinja2>=2.11.1 in /usr/local/lib/python3.6/dist-packages (from pandas-profiling>=2.3.0->pycaret==2.0) (2.11.2)
Requirement already satisfied: astropy>=4.0 in /usr/local/lib/python3.6/dist-packages (from pandas-profiling>=2.3.0->pycaret==2.0) (4.0.1.post1)
Collecting tangled-up-in-unicode>=0.0.6
  Downloading https://files.pythonhosted.org/packages/4a/e2/e588ab9298d4989ce7fdb2b97d18aac878d99dbdc379a4476a09d9271b68/tangled_up_in_unicode-0.0.6-py3-none-any.whl (3.1MB)
     |████████████████████████████████| 3.1MB 44.1MB/s 
Collecting tqdm>=4.43.0
  Downloading https://files.pythonhosted.org/packages/28/7e/281edb5bc3274dfb894d90f4dbacfceaca381c2435ec6187a2c6f329aed7/tqdm-4.48.2-py2.py3-none-any.whl (68kB)
     |████████████████████████████████| 71kB 8.2MB/s 
Collecting visions[type_image_path]==0.4.4
  Downloading https://files.pythonhosted.org/packages/4a/03/5a45d542257830cf1d9da2cdc1c0bc6f55a9212937b70fdd6d7031b46d6c/visions-0.4.4-py3-none-any.whl (59kB)
     |████████████████████████████████| 61kB 7.6MB/s 
Collecting phik>=0.9.10
  Downloading https://files.pythonhosted.org/packages/01/5a/7ef1c04ce62cd72f900c06298dc2385840550d5c653a0dbc19109a5477e6/phik-0.10.0-py3-none-any.whl (599kB)
     |████████████████████████████████| 604kB 39.8MB/s 
Requirement already satisfied: blis<0.5.0,>=0.4.0 in /usr/local/lib/python3.6/dist-packages (from spacy->pycaret==2.0) (0.4.1)
Requirement already satisfied: murmurhash<1.1.0,>=0.28.0 in /usr/local/lib/python3.6/dist-packages (from spacy->pycaret==2.0) (1.0.2)
Requirement already satisfied: preshed<3.1.0,>=3.0.2 in /usr/local/lib/python3.6/dist-packages (from spacy->pycaret==2.0) (3.0.2)
Requirement already satisfied: thinc==7.4.0 in /usr/local/lib/python3.6/dist-packages (from spacy->pycaret==2.0) (7.4.0)
Requirement already satisfied: srsly<1.1.0,>=1.0.2 in /usr/local/lib/python3.6/dist-packages (from spacy->pycaret==2.0) (1.0.2)
Requirement already satisfied: setuptools in /usr/local/lib/python3.6/dist-packages (from spacy->pycaret==2.0) (49.2.0)
Requirement already satisfied: wasabi<1.1.0,>=0.4.0 in /usr/local/lib/python3.6/dist-packages (from spacy->pycaret==2.0) (0.7.1)
Requirement already satisfied: plac<1.2.0,>=0.9.6 in /usr/local/lib/python3.6/dist-packages (from spacy->pycaret==2.0) (1.1.3)
Requirement already satisfied: cymem<2.1.0,>=2.0.2 in /usr/local/lib/python3.6/dist-packages (from spacy->pycaret==2.0) (2.0.3)
Requirement already satisfied: catalogue<1.1.0,>=0.0.7 in /usr/local/lib/python3.6/dist-packages (from spacy->pycaret==2.0) (1.0.0)
Collecting threadpoolctl>=2.0.0
  Downloading https://files.pythonhosted.org/packages/f7/12/ec3f2e203afa394a149911729357aa48affc59c20e2c1c8297a60f33f133/threadpoolctl-2.1.0-py3-none-any.whl
Requirement already satisfied: colorlover>=0.2.1 in /usr/local/lib/python3.6/dist-packages (from cufflinks>=0.17.0->pycaret==2.0) (0.3.0)
Collecting zope.interface
  Downloading https://files.pythonhosted.org/packages/57/33/565274c28a11af60b7cfc0519d46bde4125fcd7d32ebc0a81b480d0e8da6/zope.interface-5.1.0-cp36-cp36m-manylinux2010_x86_64.whl (234kB)
     |████████████████████████████████| 235kB 39.7MB/s 
Requirement already satisfied: pexpect; sys_platform != "win32" in /usr/local/lib/python3.6/dist-packages (from IPython->pycaret==2.0) (4.8.0)
Requirement already satisfied: pickleshare in /usr/local/lib/python3.6/dist-packages (from IPython->pycaret==2.0) (0.7.5)
Requirement already satisfied: prompt-toolkit<2.0.0,>=1.0.4 in /usr/local/lib/python3.6/dist-packages (from IPython->pycaret==2.0) (1.0.18)
Requirement already satisfied: simplegeneric>0.8 in /usr/local/lib/python3.6/dist-packages (from IPython->pycaret==2.0) (0.8.1)
Requirement already satisfied: pygments in /usr/local/lib/python3.6/dist-packages (from IPython->pycaret==2.0) (2.1.3)
Requirement already satisfied: decorator in /usr/local/lib/python3.6/dist-packages (from IPython->pycaret==2.0) (4.4.2)
Requirement already satisfied: smart-open>=1.2.1 in /usr/local/lib/python3.6/dist-packages (from gensim->pycaret==2.0) (2.1.0)
Requirement already satisfied: pillow in /usr/local/lib/python3.6/dist-packages (from wordcloud->pycaret==2.0) (7.0.0)
Requirement already satisfied: wheel>=0.23.0 in /usr/local/lib/python3.6/dist-packages (from pyLDAvis->pycaret==2.0) (0.34.2)
Requirement already satisfied: numexpr in /usr/local/lib/python3.6/dist-packages (from pyLDAvis->pycaret==2.0) (2.7.1)
Requirement already satisfied: pytest in /usr/local/lib/python3.6/dist-packages (from pyLDAvis->pycaret==2.0) (3.6.4)
Requirement already satisfied: future in /usr/local/lib/python3.6/dist-packages (from pyLDAvis->pycaret==2.0) (0.16.0)
Collecting funcy
  Downloading https://files.pythonhosted.org/packages/ce/4b/6ffa76544e46614123de31574ad95758c421aae391a1764921b8a81e1eae/funcy-1.14.tar.gz (548kB)
     |████████████████████████████████| 552kB 32.1MB/s 
Requirement already satisfied: graphviz in /usr/local/lib/python3.6/dist-packages (from catboost->pycaret==2.0) (0.10.1)
Requirement already satisfied: llvmlite<0.32.0,>=0.31.0dev0 in /usr/local/lib/python3.6/dist-packages (from numba!=0.47,>=0.46->umap-learn->pycaret==2.0) (0.31.0)
Requirement already satisfied: tabulate>=0.7.7 in /usr/local/lib/python3.6/dist-packages (from databricks-cli>=0.8.7->mlflow->pycaret==2.0) (0.8.7)
Collecting Mako
  Downloading https://files.pythonhosted.org/packages/a6/37/0e706200d22172eb8fa17d68a7ae22dec7631a0a92266634fb518a88a5b2/Mako-1.1.3-py2.py3-none-any.whl (75kB)
     |████████████████████████████████| 81kB 9.0MB/s 
Collecting python-editor>=0.3
  Downloading https://files.pythonhosted.org/packages/c6/d3/201fc3abe391bbae6606e6f1d598c15d367033332bd54352b12f35513717/python_editor-1.0.4-py3-none-any.whl
Collecting gitdb<5,>=4.0.1
  Downloading https://files.pythonhosted.org/packages/48/11/d1800bca0a3bae820b84b7d813ad1eff15a48a64caea9c823fc8c1b119e8/gitdb-4.0.5-py3-none-any.whl (63kB)
     |████████████████████████████████| 71kB 8.0MB/s 
Collecting azure-core<2.0.0,>=1.6.0
  Downloading https://files.pythonhosted.org/packages/8b/00/efb68e2dda82139d732090fc3b7ff47fe6f34724ea7ba31e518a854b15c1/azure_core-1.7.0-py2.py3-none-any.whl (121kB)
     |████████████████████████████████| 122kB 44.8MB/s 
Collecting msrest>=0.6.10
  Downloading https://files.pythonhosted.org/packages/d9/ed/8e1b75721ad983c1672cd968ad3ae374d2e94767edff6f0b72a15dfde933/msrest-0.6.18-py2.py3-none-any.whl (84kB)
     |████████████████████████████████| 92kB 8.6MB/s 
Collecting cryptography>=2.1.4
  Downloading https://files.pythonhosted.org/packages/ba/91/84a29d6a27fd6dfc21f475704c4d2053d58ed7a4033c2b0ce1b4ca4d03d9/cryptography-3.0-cp35-abi3-manylinux2010_x86_64.whl (2.7MB)
     |████████████████████████████████| 2.7MB 43.7MB/s 
Requirement already satisfied: prometheus_client in /usr/local/lib/python3.6/dist-packages (from prometheus-flask-exporter->mlflow->pycaret==2.0) (0.8.0)
Requirement already satisfied: Werkzeug>=0.15 in /usr/local/lib/python3.6/dist-packages (from Flask->mlflow->pycaret==2.0) (1.0.1)
Requirement already satisfied: itsdangerous>=0.24 in /usr/local/lib/python3.6/dist-packages (from Flask->mlflow->pycaret==2.0) (1.1.0)
Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.6/dist-packages (from requests>=2.17.3->mlflow->pycaret==2.0) (2020.6.20)
Requirement already satisfied: chardet<4,>=3.0.2 in /usr/local/lib/python3.6/dist-packages (from requests>=2.17.3->mlflow->pycaret==2.0) (3.0.4)
Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.6/dist-packages (from requests>=2.17.3->mlflow->pycaret==2.0) (2.10)
Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /usr/local/lib/python3.6/dist-packages (from requests>=2.17.3->mlflow->pycaret==2.0) (1.24.3)
Collecting websocket-client>=0.32.0
  Downloading https://files.pythonhosted.org/packages/4c/5f/f61b420143ed1c8dc69f9eaec5ff1ac36109d52c80de49d66e0c36c3dfdf/websocket_client-0.57.0-py2.py3-none-any.whl (200kB)
     |████████████████████████████████| 204kB 50.5MB/s 
Requirement already satisfied: ipython-genutils in /usr/local/lib/python3.6/dist-packages (from traitlets>=4.3.1->ipywidgets->pycaret==2.0) (0.2.0)
Requirement already satisfied: tornado>=4.0 in /usr/local/lib/python3.6/dist-packages (from ipykernel>=4.5.1->ipywidgets->pycaret==2.0) (5.1.1)
Requirement already satisfied: jupyter-client in /usr/local/lib/python3.6/dist-packages (from ipykernel>=4.5.1->ipywidgets->pycaret==2.0) (5.3.5)
Requirement already satisfied: notebook>=4.4.1 in /usr/local/lib/python3.6/dist-packages (from widgetsnbextension~=3.5.0->ipywidgets->pycaret==2.0) (5.3.1)
Requirement already satisfied: jupyter-core in /usr/local/lib/python3.6/dist-packages (from nbformat>=4.2.0->ipywidgets->pycaret==2.0) (4.6.3)
Requirement already satisfied: jsonschema!=2.5.0,>=2.4 in /usr/local/lib/python3.6/dist-packages (from nbformat>=4.2.0->ipywidgets->pycaret==2.0) (2.6.0)
Requirement already satisfied: MarkupSafe>=0.23 in /usr/local/lib/python3.6/dist-packages (from jinja2>=2.11.1->pandas-profiling>=2.3.0->pycaret==2.0) (1.1.1)
Requirement already satisfied: attrs>=19.3.0 in /usr/local/lib/python3.6/dist-packages (from visions[type_image_path]==0.4.4->pandas-profiling>=2.3.0->pycaret==2.0) (19.3.0)
Requirement already satisfied: networkx>=2.4 in /usr/local/lib/python3.6/dist-packages (from visions[type_image_path]==0.4.4->pandas-profiling>=2.3.0->pycaret==2.0) (2.4)
Collecting imagehash; extra == "type_image_path"
  Downloading https://files.pythonhosted.org/packages/1a/5d/cc81830be3c4705a46cdbca74439b67f1017881383ba0127c41c4cecb7b3/ImageHash-4.1.0.tar.gz (291kB)
     |████████████████████████████████| 296kB 45.3MB/s 
Requirement already satisfied: importlib-metadata>=0.20; python_version < "3.8" in /usr/local/lib/python3.6/dist-packages (from catalogue<1.1.0,>=0.0.7->spacy->pycaret==2.0) (1.7.0)
Requirement already satisfied: ptyprocess>=0.5 in /usr/local/lib/python3.6/dist-packages (from pexpect; sys_platform != "win32"->IPython->pycaret==2.0) (0.6.0)
Requirement already satisfied: wcwidth in /usr/local/lib/python3.6/dist-packages (from prompt-toolkit<2.0.0,>=1.0.4->IPython->pycaret==2.0) (0.2.5)
Requirement already satisfied: boto in /usr/local/lib/python3.6/dist-packages (from smart-open>=1.2.1->gensim->pycaret==2.0) (2.49.0)
Requirement already satisfied: boto3 in /usr/local/lib/python3.6/dist-packages (from smart-open>=1.2.1->gensim->pycaret==2.0) (1.14.33)
Requirement already satisfied: pluggy<0.8,>=0.5 in /usr/local/lib/python3.6/dist-packages (from pytest->pyLDAvis->pycaret==2.0) (0.7.1)
Requirement already satisfied: py>=1.5.0 in /usr/local/lib/python3.6/dist-packages (from pytest->pyLDAvis->pycaret==2.0) (1.9.0)
Requirement already satisfied: atomicwrites>=1.0 in /usr/local/lib/python3.6/dist-packages (from pytest->pyLDAvis->pycaret==2.0) (1.4.0)
Requirement already satisfied: more-itertools>=4.0.0 in /usr/local/lib/python3.6/dist-packages (from pytest->pyLDAvis->pycaret==2.0) (8.4.0)
Collecting smmap<4,>=3.0.1
  Downloading https://files.pythonhosted.org/packages/b0/9a/4d409a6234eb940e6a78dfdfc66156e7522262f5f2fecca07dc55915952d/smmap-3.0.4-py2.py3-none-any.whl
Collecting isodate>=0.6.0
  Downloading https://files.pythonhosted.org/packages/9b/9f/b36f7774ff5ea8e428fdcfc4bb332c39ee5b9362ddd3d40d9516a55221b2/isodate-0.6.0-py2.py3-none-any.whl (45kB)
     |████████████████████████████████| 51kB 5.9MB/s 
Requirement already satisfied: requests-oauthlib>=0.5.0 in /usr/local/lib/python3.6/dist-packages (from msrest>=0.6.10->azure-storage-blob>=12.0->mlflow->pycaret==2.0) (1.3.0)
Requirement already satisfied: cffi!=1.11.3,>=1.8 in /usr/local/lib/python3.6/dist-packages (from cryptography>=2.1.4->azure-storage-blob>=12.0->mlflow->pycaret==2.0) (1.14.1)
Requirement already satisfied: pyzmq>=13 in /usr/local/lib/python3.6/dist-packages (from jupyter-client->ipykernel>=4.5.1->ipywidgets->pycaret==2.0) (19.0.2)
Requirement already satisfied: nbconvert in /usr/local/lib/python3.6/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets->pycaret==2.0) (5.6.1)
Requirement already satisfied: terminado>=0.8.1 in /usr/local/lib/python3.6/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets->pycaret==2.0) (0.8.3)
Requirement already satisfied: Send2Trash in /usr/local/lib/python3.6/dist-packages (from notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets->pycaret==2.0) (1.5.0)
Requirement already satisfied: PyWavelets in /usr/local/lib/python3.6/dist-packages (from imagehash; extra == "type_image_path"->visions[type_image_path]==0.4.4->pandas-profiling>=2.3.0->pycaret==2.0) (1.1.1)
Requirement already satisfied: zipp>=0.5 in /usr/local/lib/python3.6/dist-packages (from importlib-metadata>=0.20; python_version < "3.8"->catalogue<1.1.0,>=0.0.7->spacy->pycaret==2.0) (3.1.0)
Requirement already satisfied: botocore<1.18.0,>=1.17.33 in /usr/local/lib/python3.6/dist-packages (from boto3->smart-open>=1.2.1->gensim->pycaret==2.0) (1.17.33)
Requirement already satisfied: s3transfer<0.4.0,>=0.3.0 in /usr/local/lib/python3.6/dist-packages (from boto3->smart-open>=1.2.1->gensim->pycaret==2.0) (0.3.3)
Requirement already satisfied: jmespath<1.0.0,>=0.7.1 in /usr/local/lib/python3.6/dist-packages (from boto3->smart-open>=1.2.1->gensim->pycaret==2.0) (0.10.0)
Requirement already satisfied: oauthlib>=3.0.0 in /usr/local/lib/python3.6/dist-packages (from requests-oauthlib>=0.5.0->msrest>=0.6.10->azure-storage-blob>=12.0->mlflow->pycaret==2.0) (3.1.0)
Requirement already satisfied: pycparser in /usr/local/lib/python3.6/dist-packages (from cffi!=1.11.3,>=1.8->cryptography>=2.1.4->azure-storage-blob>=12.0->mlflow->pycaret==2.0) (2.20)
Requirement already satisfied: defusedxml in /usr/local/lib/python3.6/dist-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets->pycaret==2.0) (0.6.0)
Requirement already satisfied: testpath in /usr/local/lib/python3.6/dist-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets->pycaret==2.0) (0.4.4)
Requirement already satisfied: pandocfilters>=1.4.1 in /usr/local/lib/python3.6/dist-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets->pycaret==2.0) (1.4.2)
Requirement already satisfied: mistune<2,>=0.8.1 in /usr/local/lib/python3.6/dist-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets->pycaret==2.0) (0.8.4)
Requirement already satisfied: bleach in /usr/local/lib/python3.6/dist-packages (from nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets->pycaret==2.0) (3.1.5)
Requirement already satisfied: docutils<0.16,>=0.10 in /usr/local/lib/python3.6/dist-packages (from botocore<1.18.0,>=1.17.33->boto3->smart-open>=1.2.1->gensim->pycaret==2.0) (0.15.2)
Requirement already satisfied: webencodings in /usr/local/lib/python3.6/dist-packages (from bleach->nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets->pycaret==2.0) (0.5.1)
Requirement already satisfied: packaging in /usr/local/lib/python3.6/dist-packages (from bleach->nbconvert->notebook>=4.4.1->widgetsnbextension~=3.5.0->ipywidgets->pycaret==2.0) (20.4)
Building wheels for collected packages: alembic
  Building wheel for alembic (PEP 517) ... done
  Created wheel for alembic: filename=alembic-1.4.2-cp36-none-any.whl size=159543 sha256=06ace8b7b91348fbaed3fa9a7b26ff102b4f539c521ff8b6f9bfdef088931eca
  Stored in directory: /root/.cache/pip/wheels/1f/04/83/76023f7a4c14688c0b5c2682a96392cfdd3ee4449eaaa287ef
Successfully built alembic
Building wheels for collected packages: pyod, pyLDAvis, databricks-cli, prometheus-flask-exporter, querystring-parser, sqlalchemy, combo, suod, htmlmin, funcy, imagehash
  Building wheel for pyod (setup.py) ... done
  Created wheel for pyod: filename=pyod-0.8.1-cp36-none-any.whl size=105653 sha256=c899b1ef39e8dc09b519cc1be1c2d0ce9cec77162f607442747ff2ef4eaa7bed
  Stored in directory: /root/.cache/pip/wheels/2e/ca/18/727e9d98a41f5f4385a97d5b429f3a9c8fbee13f9780c18642
  Building wheel for pyLDAvis (setup.py) ... done
  Created wheel for pyLDAvis: filename=pyLDAvis-2.1.2-py2.py3-none-any.whl size=97711 sha256=ae97d19ffe6299d0fd60df3ec40fd4770ff7c3edfc902fdf8c527b2945862c2e
  Stored in directory: /root/.cache/pip/wheels/98/71/24/513a99e58bb6b8465bae4d2d5e9dba8f0bef8179e3051ac414
  Building wheel for databricks-cli (setup.py) ... done
  Created wheel for databricks-cli: filename=databricks_cli-0.11.0-cp36-none-any.whl size=90300 sha256=35c931b30ff6d0817c52e8e5f2771f93ae12e125d229e6e12b530973f405f877
  Stored in directory: /root/.cache/pip/wheels/63/d0/4f/3deeca1f4c47a6aca7c2c6a6e2bf272391565dc86a7718a59b
  Building wheel for prometheus-flask-exporter (setup.py) ... done
  Created wheel for prometheus-flask-exporter: filename=prometheus_flask_exporter-0.15.4-cp36-none-any.whl size=16454 sha256=4e3e01f48cf5ed377de2a57dd125ecaf7e436aa931dbe26c48eef4d15f435403
  Stored in directory: /root/.cache/pip/wheels/4f/b4/70/b18fa12c1c0a30fd542767dbbcdac225c6aae012fa1b3124e4
  Building wheel for querystring-parser (setup.py) ... done
  Created wheel for querystring-parser: filename=querystring_parser-1.2.4-cp36-none-any.whl size=7079 sha256=d22dec76fd72f2ab6552f6d7a8c2823862e97afd58f153afd5f152cb8466b2a6
  Stored in directory: /root/.cache/pip/wheels/1e/41/34/23ebf5d1089a9aed847951e0ee375426eb4ad0a7079d88d41e
  Building wheel for sqlalchemy (setup.py) ... done
  Created wheel for sqlalchemy: filename=SQLAlchemy-1.3.13-cp36-cp36m-linux_x86_64.whl size=1217122 sha256=23749b51d34b91d033060c972f32b9c87047b672350bbc7dc4aa460121452719
  Stored in directory: /root/.cache/pip/wheels/b3/35/98/4c9cb3fd63d21d5606b972dd70643769745adf60e622467b71
  Building wheel for combo (setup.py) ... done
  Created wheel for combo: filename=combo-0.1.1-cp36-none-any.whl size=42111 sha256=327ca116529791bdf86a4e9099769a797ca492f80dd3e6a6e468c460c8f3e590
  Stored in directory: /root/.cache/pip/wheels/55/ec/e5/a2331372c676c467e70c6646e646edf6997d5c4905b8c0f5e6
  Building wheel for suod (setup.py) ... done
  Created wheel for suod: filename=suod-0.0.4-cp36-none-any.whl size=2167157 sha256=564306ff92a93409b2bf6b81c1b1212eff5896c01721b83b1d82b57518a87be3
  Stored in directory: /root/.cache/pip/wheels/57/55/e5/a4fca65bba231f6d0115059b589148774b41faea25b3f2aa27
  Building wheel for htmlmin (setup.py) ... done
  Created wheel for htmlmin: filename=htmlmin-0.1.12-cp36-none-any.whl size=27084 sha256=da60b51e32bb8929719684a8a60557ffbcbd982ef56b40019b5cadc048ec5be1
  Stored in directory: /root/.cache/pip/wheels/43/07/ac/7c5a9d708d65247ac1f94066cf1db075540b85716c30255459
  Building wheel for funcy (setup.py) ... done
  Created wheel for funcy: filename=funcy-1.14-py2.py3-none-any.whl size=32042 sha256=354b55cd981e15dae9a332dc8e242e16476e859847ff5cea23e340f06e164f6e
  Stored in directory: /root/.cache/pip/wheels/20/5a/d8/1d875df03deae6f178dfdf70238cca33f948ef8a6f5209f2eb
  Building wheel for imagehash (setup.py) ... done
  Created wheel for imagehash: filename=ImageHash-4.1.0-py2.py3-none-any.whl size=291990 sha256=b0694f24587fc5850a57b6b29f05a36c4734cb6c8cb79052a66d714559ed7e24
  Stored in directory: /root/.cache/pip/wheels/07/1c/dc/6831446f09feb8cc199ec73a0f2f0703253f6ae013a22f4be9
Successfully built pyod pyLDAvis databricks-cli prometheus-flask-exporter querystring-parser sqlalchemy combo suod htmlmin funcy imagehash
Installing collected packages: threadpoolctl, scikit-learn, yellowbrick, gunicorn, databricks-cli, Mako, python-editor, sqlalchemy, alembic, smmap, gitdb, gitpython, azure-core, isodate, msrest, cryptography, azure-storage-blob, gorilla, prometheus-flask-exporter, querystring-parser, websocket-client, docker, mlflow, datefinder, combo, suod, pyod, htmlmin, confuse, tangled-up-in-unicode, tqdm, imagehash, visions, phik, pandas-profiling, lightgbm, zope.interface, DateTime, funcy, pyLDAvis, kmodes, catboost, pycaret
  Found existing installation: scikit-learn 0.22.2.post1
    Uninstalling scikit-learn-0.22.2.post1:
      Successfully uninstalled scikit-learn-0.22.2.post1
  Found existing installation: yellowbrick 0.9.1
    Uninstalling yellowbrick-0.9.1:
      Successfully uninstalled yellowbrick-0.9.1
  Found existing installation: SQLAlchemy 1.3.18
    Uninstalling SQLAlchemy-1.3.18:
      Successfully uninstalled SQLAlchemy-1.3.18
  Found existing installation: tqdm 4.41.1
    Uninstalling tqdm-4.41.1:
      Successfully uninstalled tqdm-4.41.1
  Found existing installation: pandas-profiling 1.4.1
    Uninstalling pandas-profiling-1.4.1:
      Successfully uninstalled pandas-profiling-1.4.1
  Found existing installation: lightgbm 2.2.3
    Uninstalling lightgbm-2.2.3:
      Successfully uninstalled lightgbm-2.2.3
Successfully installed DateTime-4.3 Mako-1.1.3 alembic-1.4.2 azure-core-1.7.0 azure-storage-blob-12.3.2 catboost-0.24 combo-0.1.1 confuse-1.3.0 cryptography-3.0 databricks-cli-0.11.0 datefinder-0.7.1 docker-4.2.2 funcy-1.14 gitdb-4.0.5 gitpython-3.1.7 gorilla-0.3.0 gunicorn-20.0.4 htmlmin-0.1.12 imagehash-4.1.0 isodate-0.6.0 kmodes-0.10.2 lightgbm-2.3.1 mlflow-1.10.0 msrest-0.6.18 pandas-profiling-2.8.0 phik-0.10.0 prometheus-flask-exporter-0.15.4 pyLDAvis-2.1.2 pycaret-2.0 pyod-0.8.1 python-editor-1.0.4 querystring-parser-1.2.4 scikit-learn-0.23.2 smmap-3.0.4 sqlalchemy-1.3.13 suod-0.0.4 tangled-up-in-unicode-0.0.6 threadpoolctl-2.1.0 tqdm-4.48.2 visions-0.4.4 websocket-client-0.57.0 yellowbrick-1.1 zope.interface-5.1.0

FIFA Player Market Value Prediction¶

Import Libraries¶

Importing the necessary dependancies for the Pycaret library

In [3]:

from pycaret.regression import *
from pycaret.utils import enable_colab
enable_colab()

Colab mode activated.

In [4]:

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline
import seaborn as sns
import plotly.express as px
import plotly.graph_objects as go
import folium
import copy
from folium import plugins
plt.rcParams['figure.figsize'] = 10, 12
import warnings
warnings.filterwarnings('ignore')

/usr/local/lib/python3.6/dist-packages/statsmodels/tools/_testing.py:19: FutureWarning: pandas.util.testing is deprecated. Use the functions in the public API at pandas.testing instead.
  import pandas.util.testing as tm

Data Preprocessing¶

In [5]:

fifaInput= pd.read_csv("/content/drive/My Drive/fifa.csv")

In [29]:

fifa = copy.deepcopy(fifaInput)
to_Drop = ["ID", "Photo", "Flag", "Club Logo", "Real Face", "Loaned From", "Name", "Club"]
fifa = fifa.drop(columns = to_Drop)
fifa['Value'] = fifa['Value'].str.split('\u20AC').str[1]
fifa['Wage'] = fifa['Wage'].str.split('\u20AC').str[1]
fifa['Release Clause'] = fifa['Release Clause'].str.split('\u20AC').str[1]
fifa

Out[29]:

	Unnamed: 0	Age	Nationality	Overall	Potential	Value	Wage	Special	Preferred Foot	International Reputation	Weak Foot	Skill Moves	Work Rate	Body Type	Position	Jersey Number	Joined	Contract Valid Until	Height	Weight	LS	ST	RS	LW	LF	CF	RF	RW	LAM	CAM	RAM	LM	LCM	CM	RCM	RM	LWB	LDM	CDM	RDM	RWB	LB	LCB	CB	RCB	RB	Crossing	Finishing	HeadingAccuracy	ShortPassing	Volleys	Dribbling	Curve	FKAccuracy	LongPassing	BallControl	Acceleration	SprintSpeed	Agility	Reactions	Balance	ShotPower	Jumping	Stamina	Strength	LongShots	Aggression	Interceptions	Positioning	Vision	Penalties	Composure	Marking	StandingTackle	SlidingTackle	GKDiving	GKHandling	GKKicking	GKPositioning	GKReflexes	Release Clause
0	0	31	Argentina	94	94	110.5M	565K	2202	Left	5.0	4.0	4.0	Medium/ Medium	Messi	RF	10.0	Jul 1, 2004	2021	5'7	159lbs	88+2	88+2	88+2	92+2	93+2	93+2	93+2	92+2	93+2	93+2	93+2	91+2	84+2	84+2	84+2	91+2	64+2	61+2	61+2	61+2	64+2	59+2	47+2	47+2	47+2	59+2	84.0	95.0	70.0	90.0	86.0	97.0	93.0	94.0	87.0	96.0	91.0	86.0	91.0	95.0	95.0	85.0	68.0	72.0	59.0	94.0	48.0	22.0	94.0	94.0	75.0	96.0	33.0	28.0	26.0	6.0	11.0	15.0	14.0	8.0	226.5M
1	1	33	Portugal	94	94	77M	405K	2228	Right	5.0	4.0	5.0	High/ Low	C. Ronaldo	ST	7.0	Jul 10, 2018	2022	6'2	183lbs	91+3	91+3	91+3	89+3	90+3	90+3	90+3	89+3	88+3	88+3	88+3	88+3	81+3	81+3	81+3	88+3	65+3	61+3	61+3	61+3	65+3	61+3	53+3	53+3	53+3	61+3	84.0	94.0	89.0	81.0	87.0	88.0	81.0	76.0	77.0	94.0	89.0	91.0	87.0	96.0	70.0	95.0	95.0	88.0	79.0	93.0	63.0	29.0	95.0	82.0	85.0	95.0	28.0	31.0	23.0	7.0	11.0	15.0	14.0	11.0	127.1M
2	2	26	Brazil	92	93	118.5M	290K	2143	Right	5.0	5.0	5.0	High/ Medium	Neymar	LW	10.0	Aug 3, 2017	2022	5'9	150lbs	84+3	84+3	84+3	89+3	89+3	89+3	89+3	89+3	89+3	89+3	89+3	88+3	81+3	81+3	81+3	88+3	65+3	60+3	60+3	60+3	65+3	60+3	47+3	47+3	47+3	60+3	79.0	87.0	62.0	84.0	84.0	96.0	88.0	87.0	78.0	95.0	94.0	90.0	96.0	94.0	84.0	80.0	61.0	81.0	49.0	82.0	56.0	36.0	89.0	87.0	81.0	94.0	27.0	24.0	33.0	9.0	9.0	15.0	15.0	11.0	228.1M
3	3	27	Spain	91	93	72M	260K	1471	Right	4.0	3.0	1.0	Medium/ Medium	Lean	GK	1.0	Jul 1, 2011	2020	6'4	168lbs	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	17.0	13.0	21.0	50.0	13.0	18.0	21.0	19.0	51.0	42.0	57.0	58.0	60.0	90.0	43.0	31.0	67.0	43.0	64.0	12.0	38.0	30.0	12.0	68.0	40.0	68.0	15.0	21.0	13.0	90.0	85.0	87.0	88.0	94.0	138.6M
4	4	27	Belgium	91	92	102M	355K	2281	Right	4.0	5.0	4.0	High/ High	Normal	RCM	7.0	Aug 30, 2015	2023	5'11	154lbs	82+3	82+3	82+3	87+3	87+3	87+3	87+3	87+3	88+3	88+3	88+3	88+3	87+3	87+3	87+3	88+3	77+3	77+3	77+3	77+3	77+3	73+3	66+3	66+3	66+3	73+3	93.0	82.0	55.0	92.0	82.0	86.0	85.0	83.0	91.0	91.0	78.0	76.0	79.0	91.0	77.0	91.0	63.0	90.0	75.0	91.0	76.0	61.0	87.0	94.0	79.0	88.0	68.0	58.0	51.0	15.0	13.0	5.0	10.0	13.0	196.4M
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
18202	18202	19	England	47	65	60K	1K	1307	Right	1.0	2.0	2.0	Medium/ Medium	Lean	CM	22.0	May 3, 2017	2019	5'9	134lbs	42+2	42+2	42+2	44+2	44+2	44+2	44+2	44+2	45+2	45+2	45+2	44+2	45+2	45+2	45+2	44+2	44+2	45+2	45+2	45+2	44+2	45+2	45+2	45+2	45+2	45+2	34.0	38.0	40.0	49.0	25.0	42.0	30.0	34.0	45.0	43.0	54.0	57.0	60.0	49.0	76.0	43.0	55.0	40.0	47.0	38.0	46.0	46.0	39.0	52.0	43.0	45.0	40.0	48.0	47.0	10.0	13.0	7.0	8.0	9.0	143K
18203	18203	19	Sweden	47	63	60K	1K	1098	Right	1.0	2.0	2.0	Medium/ Medium	Normal	ST	21.0	Mar 19, 2018	2020	6'3	170lbs	45+2	45+2	45+2	39+2	42+2	42+2	42+2	39+2	40+2	40+2	40+2	38+2	35+2	35+2	35+2	38+2	30+2	31+2	31+2	31+2	30+2	29+2	32+2	32+2	32+2	29+2	23.0	52.0	52.0	43.0	36.0	39.0	32.0	20.0	25.0	40.0	41.0	39.0	38.0	40.0	52.0	41.0	47.0	43.0	67.0	42.0	47.0	16.0	46.0	33.0	43.0	42.0	22.0	15.0	19.0	10.0	9.0	9.0	5.0	12.0	113K
18204	18204	16	England	47	67	60K	1K	1189	Right	1.0	3.0	2.0	Medium/ Medium	Normal	ST	33.0	Jul 1, 2017	2021	5'8	148lbs	45+2	45+2	45+2	45+2	46+2	46+2	46+2	45+2	44+2	44+2	44+2	44+2	38+2	38+2	38+2	44+2	34+2	30+2	30+2	30+2	34+2	33+2	28+2	28+2	28+2	33+2	25.0	40.0	46.0	38.0	38.0	45.0	38.0	27.0	28.0	44.0	70.0	69.0	50.0	47.0	58.0	45.0	60.0	55.0	32.0	45.0	32.0	15.0	48.0	43.0	55.0	41.0	32.0	13.0	11.0	6.0	5.0	10.0	6.0	13.0	165K
18205	18205	17	England	47	66	60K	1K	1228	Right	1.0	3.0	2.0	Medium/ Medium	Lean	RW	34.0	Apr 24, 2018	2019	5'10	154lbs	47+2	47+2	47+2	47+2	46+2	46+2	46+2	47+2	45+2	45+2	45+2	46+2	39+2	39+2	39+2	46+2	36+2	32+2	32+2	32+2	36+2	35+2	31+2	31+2	31+2	35+2	44.0	50.0	39.0	42.0	40.0	51.0	34.0	32.0	32.0	52.0	61.0	60.0	52.0	21.0	71.0	64.0	42.0	40.0	48.0	34.0	33.0	22.0	44.0	47.0	50.0	46.0	20.0	25.0	27.0	14.0	6.0	14.0	8.0	9.0	143K
18206	18206	16	England	46	66	60K	1K	1321	Right	1.0	3.0	2.0	Medium/ Medium	Lean	CM	33.0	Oct 30, 2018	2019	5'10	176lbs	43+2	43+2	43+2	45+2	44+2	44+2	44+2	45+2	45+2	45+2	45+2	46+2	45+2	45+2	45+2	46+2	46+2	46+2	46+2	46+2	46+2	46+2	47+2	47+2	47+2	46+2	41.0	34.0	46.0	48.0	30.0	43.0	40.0	34.0	44.0	51.0	57.0	55.0	55.0	51.0	63.0	43.0	62.0	47.0	60.0	32.0	56.0	42.0	34.0	49.0	33.0	43.0	40.0	43.0	50.0	10.0	15.0	9.0	12.0	9.0	165K

18207 rows × 81 columns

In [30]:

repl_dict = {'[kK]': '*1000', '[mM]': '*1000000', '[bB]': '*1000000000', }

# fifa = fifa.fillna(fifa.mean())
fifa['Value'] = fifa['Value'].replace(repl_dict, regex=True)
new = fifa["Value"].str.split("*", n = 1, expand = True) 
#print(new)
# making separate first name column from new data frame 
fifa["Value1"]= new[0] 
fifa["Value2"]= new[1]
fifa['Value1'] = pd.to_numeric(fifa['Value1'], errors='coerce')
fifa['Value2'] = pd.to_numeric(fifa['Value2'], errors='coerce')
fifa['Value'] = fifa['Value1'] * fifa['Value2']
fifa = fifa.drop(columns = ['Value1', 'Value2'])
fifa

Out[30]:

	Unnamed: 0	Age	Nationality	Overall	Potential	Value	Wage	Special	Preferred Foot	International Reputation	Weak Foot	Skill Moves	Work Rate	Body Type	Position	Jersey Number	Joined	Contract Valid Until	Height	Weight	LS	ST	RS	LW	LF	CF	RF	RW	LAM	CAM	RAM	LM	LCM	CM	RCM	RM	LWB	LDM	CDM	RDM	RWB	LB	LCB	CB	RCB	RB	Crossing	Finishing	HeadingAccuracy	ShortPassing	Volleys	Dribbling	Curve	FKAccuracy	LongPassing	BallControl	Acceleration	SprintSpeed	Agility	Reactions	Balance	ShotPower	Jumping	Stamina	Strength	LongShots	Aggression	Interceptions	Positioning	Vision	Penalties	Composure	Marking	StandingTackle	SlidingTackle	GKDiving	GKHandling	GKKicking	GKPositioning	GKReflexes	Release Clause
0	0	31	Argentina	94	94	110500000.0	565K	2202	Left	5.0	4.0	4.0	Medium/ Medium	Messi	RF	10.0	Jul 1, 2004	2021	5'7	159lbs	88+2	88+2	88+2	92+2	93+2	93+2	93+2	92+2	93+2	93+2	93+2	91+2	84+2	84+2	84+2	91+2	64+2	61+2	61+2	61+2	64+2	59+2	47+2	47+2	47+2	59+2	84.0	95.0	70.0	90.0	86.0	97.0	93.0	94.0	87.0	96.0	91.0	86.0	91.0	95.0	95.0	85.0	68.0	72.0	59.0	94.0	48.0	22.0	94.0	94.0	75.0	96.0	33.0	28.0	26.0	6.0	11.0	15.0	14.0	8.0	226.5M
1	1	33	Portugal	94	94	77000000.0	405K	2228	Right	5.0	4.0	5.0	High/ Low	C. Ronaldo	ST	7.0	Jul 10, 2018	2022	6'2	183lbs	91+3	91+3	91+3	89+3	90+3	90+3	90+3	89+3	88+3	88+3	88+3	88+3	81+3	81+3	81+3	88+3	65+3	61+3	61+3	61+3	65+3	61+3	53+3	53+3	53+3	61+3	84.0	94.0	89.0	81.0	87.0	88.0	81.0	76.0	77.0	94.0	89.0	91.0	87.0	96.0	70.0	95.0	95.0	88.0	79.0	93.0	63.0	29.0	95.0	82.0	85.0	95.0	28.0	31.0	23.0	7.0	11.0	15.0	14.0	11.0	127.1M
2	2	26	Brazil	92	93	118500000.0	290K	2143	Right	5.0	5.0	5.0	High/ Medium	Neymar	LW	10.0	Aug 3, 2017	2022	5'9	150lbs	84+3	84+3	84+3	89+3	89+3	89+3	89+3	89+3	89+3	89+3	89+3	88+3	81+3	81+3	81+3	88+3	65+3	60+3	60+3	60+3	65+3	60+3	47+3	47+3	47+3	60+3	79.0	87.0	62.0	84.0	84.0	96.0	88.0	87.0	78.0	95.0	94.0	90.0	96.0	94.0	84.0	80.0	61.0	81.0	49.0	82.0	56.0	36.0	89.0	87.0	81.0	94.0	27.0	24.0	33.0	9.0	9.0	15.0	15.0	11.0	228.1M
3	3	27	Spain	91	93	72000000.0	260K	1471	Right	4.0	3.0	1.0	Medium/ Medium	Lean	GK	1.0	Jul 1, 2011	2020	6'4	168lbs	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	17.0	13.0	21.0	50.0	13.0	18.0	21.0	19.0	51.0	42.0	57.0	58.0	60.0	90.0	43.0	31.0	67.0	43.0	64.0	12.0	38.0	30.0	12.0	68.0	40.0	68.0	15.0	21.0	13.0	90.0	85.0	87.0	88.0	94.0	138.6M
4	4	27	Belgium	91	92	102000000.0	355K	2281	Right	4.0	5.0	4.0	High/ High	Normal	RCM	7.0	Aug 30, 2015	2023	5'11	154lbs	82+3	82+3	82+3	87+3	87+3	87+3	87+3	87+3	88+3	88+3	88+3	88+3	87+3	87+3	87+3	88+3	77+3	77+3	77+3	77+3	77+3	73+3	66+3	66+3	66+3	73+3	93.0	82.0	55.0	92.0	82.0	86.0	85.0	83.0	91.0	91.0	78.0	76.0	79.0	91.0	77.0	91.0	63.0	90.0	75.0	91.0	76.0	61.0	87.0	94.0	79.0	88.0	68.0	58.0	51.0	15.0	13.0	5.0	10.0	13.0	196.4M
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
18202	18202	19	England	47	65	60000.0	1K	1307	Right	1.0	2.0	2.0	Medium/ Medium	Lean	CM	22.0	May 3, 2017	2019	5'9	134lbs	42+2	42+2	42+2	44+2	44+2	44+2	44+2	44+2	45+2	45+2	45+2	44+2	45+2	45+2	45+2	44+2	44+2	45+2	45+2	45+2	44+2	45+2	45+2	45+2	45+2	45+2	34.0	38.0	40.0	49.0	25.0	42.0	30.0	34.0	45.0	43.0	54.0	57.0	60.0	49.0	76.0	43.0	55.0	40.0	47.0	38.0	46.0	46.0	39.0	52.0	43.0	45.0	40.0	48.0	47.0	10.0	13.0	7.0	8.0	9.0	143K
18203	18203	19	Sweden	47	63	60000.0	1K	1098	Right	1.0	2.0	2.0	Medium/ Medium	Normal	ST	21.0	Mar 19, 2018	2020	6'3	170lbs	45+2	45+2	45+2	39+2	42+2	42+2	42+2	39+2	40+2	40+2	40+2	38+2	35+2	35+2	35+2	38+2	30+2	31+2	31+2	31+2	30+2	29+2	32+2	32+2	32+2	29+2	23.0	52.0	52.0	43.0	36.0	39.0	32.0	20.0	25.0	40.0	41.0	39.0	38.0	40.0	52.0	41.0	47.0	43.0	67.0	42.0	47.0	16.0	46.0	33.0	43.0	42.0	22.0	15.0	19.0	10.0	9.0	9.0	5.0	12.0	113K
18204	18204	16	England	47	67	60000.0	1K	1189	Right	1.0	3.0	2.0	Medium/ Medium	Normal	ST	33.0	Jul 1, 2017	2021	5'8	148lbs	45+2	45+2	45+2	45+2	46+2	46+2	46+2	45+2	44+2	44+2	44+2	44+2	38+2	38+2	38+2	44+2	34+2	30+2	30+2	30+2	34+2	33+2	28+2	28+2	28+2	33+2	25.0	40.0	46.0	38.0	38.0	45.0	38.0	27.0	28.0	44.0	70.0	69.0	50.0	47.0	58.0	45.0	60.0	55.0	32.0	45.0	32.0	15.0	48.0	43.0	55.0	41.0	32.0	13.0	11.0	6.0	5.0	10.0	6.0	13.0	165K
18205	18205	17	England	47	66	60000.0	1K	1228	Right	1.0	3.0	2.0	Medium/ Medium	Lean	RW	34.0	Apr 24, 2018	2019	5'10	154lbs	47+2	47+2	47+2	47+2	46+2	46+2	46+2	47+2	45+2	45+2	45+2	46+2	39+2	39+2	39+2	46+2	36+2	32+2	32+2	32+2	36+2	35+2	31+2	31+2	31+2	35+2	44.0	50.0	39.0	42.0	40.0	51.0	34.0	32.0	32.0	52.0	61.0	60.0	52.0	21.0	71.0	64.0	42.0	40.0	48.0	34.0	33.0	22.0	44.0	47.0	50.0	46.0	20.0	25.0	27.0	14.0	6.0	14.0	8.0	9.0	143K
18206	18206	16	England	46	66	60000.0	1K	1321	Right	1.0	3.0	2.0	Medium/ Medium	Lean	CM	33.0	Oct 30, 2018	2019	5'10	176lbs	43+2	43+2	43+2	45+2	44+2	44+2	44+2	45+2	45+2	45+2	45+2	46+2	45+2	45+2	45+2	46+2	46+2	46+2	46+2	46+2	46+2	46+2	47+2	47+2	47+2	46+2	41.0	34.0	46.0	48.0	30.0	43.0	40.0	34.0	44.0	51.0	57.0	55.0	55.0	51.0	63.0	43.0	62.0	47.0	60.0	32.0	56.0	42.0	34.0	49.0	33.0	43.0	40.0	43.0	50.0	10.0	15.0	9.0	12.0	9.0	165K

18207 rows × 81 columns

In [31]:

fifa['Wage'] = fifa['Wage'].replace(repl_dict, regex=True)
new = fifa["Wage"].str.split("*", n = 1, expand = True) 
#print(new)
# making separate first name column from new data frame 
fifa["Wage1"]= new[0] 
fifa["Wage2"]= new[1]
fifa['Wage1'] = pd.to_numeric(fifa['Wage1'], errors='coerce')
fifa['Wage2'] = pd.to_numeric(fifa['Wage2'], errors='coerce')
fifa['Wage'] = fifa['Wage1'] * fifa['Wage2']
fifa = fifa.drop(columns = ['Wage1', 'Wage2'])

fifa

Out[31]:

	Unnamed: 0	Age	Nationality	Overall	Potential	Value	Wage	Special	Preferred Foot	International Reputation	Weak Foot	Skill Moves	Work Rate	Body Type	Position	Jersey Number	Joined	Contract Valid Until	Height	Weight	LS	ST	RS	LW	LF	CF	RF	RW	LAM	CAM	RAM	LM	LCM	CM	RCM	RM	LWB	LDM	CDM	RDM	RWB	LB	LCB	CB	RCB	RB	Crossing	Finishing	HeadingAccuracy	ShortPassing	Volleys	Dribbling	Curve	FKAccuracy	LongPassing	BallControl	Acceleration	SprintSpeed	Agility	Reactions	Balance	ShotPower	Jumping	Stamina	Strength	LongShots	Aggression	Interceptions	Positioning	Vision	Penalties	Composure	Marking	StandingTackle	SlidingTackle	GKDiving	GKHandling	GKKicking	GKPositioning	GKReflexes	Release Clause
0	0	31	Argentina	94	94	110500000.0	565000.0	2202	Left	5.0	4.0	4.0	Medium/ Medium	Messi	RF	10.0	Jul 1, 2004	2021	5'7	159lbs	88+2	88+2	88+2	92+2	93+2	93+2	93+2	92+2	93+2	93+2	93+2	91+2	84+2	84+2	84+2	91+2	64+2	61+2	61+2	61+2	64+2	59+2	47+2	47+2	47+2	59+2	84.0	95.0	70.0	90.0	86.0	97.0	93.0	94.0	87.0	96.0	91.0	86.0	91.0	95.0	95.0	85.0	68.0	72.0	59.0	94.0	48.0	22.0	94.0	94.0	75.0	96.0	33.0	28.0	26.0	6.0	11.0	15.0	14.0	8.0	226.5M
1	1	33	Portugal	94	94	77000000.0	405000.0	2228	Right	5.0	4.0	5.0	High/ Low	C. Ronaldo	ST	7.0	Jul 10, 2018	2022	6'2	183lbs	91+3	91+3	91+3	89+3	90+3	90+3	90+3	89+3	88+3	88+3	88+3	88+3	81+3	81+3	81+3	88+3	65+3	61+3	61+3	61+3	65+3	61+3	53+3	53+3	53+3	61+3	84.0	94.0	89.0	81.0	87.0	88.0	81.0	76.0	77.0	94.0	89.0	91.0	87.0	96.0	70.0	95.0	95.0	88.0	79.0	93.0	63.0	29.0	95.0	82.0	85.0	95.0	28.0	31.0	23.0	7.0	11.0	15.0	14.0	11.0	127.1M
2	2	26	Brazil	92	93	118500000.0	290000.0	2143	Right	5.0	5.0	5.0	High/ Medium	Neymar	LW	10.0	Aug 3, 2017	2022	5'9	150lbs	84+3	84+3	84+3	89+3	89+3	89+3	89+3	89+3	89+3	89+3	89+3	88+3	81+3	81+3	81+3	88+3	65+3	60+3	60+3	60+3	65+3	60+3	47+3	47+3	47+3	60+3	79.0	87.0	62.0	84.0	84.0	96.0	88.0	87.0	78.0	95.0	94.0	90.0	96.0	94.0	84.0	80.0	61.0	81.0	49.0	82.0	56.0	36.0	89.0	87.0	81.0	94.0	27.0	24.0	33.0	9.0	9.0	15.0	15.0	11.0	228.1M
3	3	27	Spain	91	93	72000000.0	260000.0	1471	Right	4.0	3.0	1.0	Medium/ Medium	Lean	GK	1.0	Jul 1, 2011	2020	6'4	168lbs	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	17.0	13.0	21.0	50.0	13.0	18.0	21.0	19.0	51.0	42.0	57.0	58.0	60.0	90.0	43.0	31.0	67.0	43.0	64.0	12.0	38.0	30.0	12.0	68.0	40.0	68.0	15.0	21.0	13.0	90.0	85.0	87.0	88.0	94.0	138.6M
4	4	27	Belgium	91	92	102000000.0	355000.0	2281	Right	4.0	5.0	4.0	High/ High	Normal	RCM	7.0	Aug 30, 2015	2023	5'11	154lbs	82+3	82+3	82+3	87+3	87+3	87+3	87+3	87+3	88+3	88+3	88+3	88+3	87+3	87+3	87+3	88+3	77+3	77+3	77+3	77+3	77+3	73+3	66+3	66+3	66+3	73+3	93.0	82.0	55.0	92.0	82.0	86.0	85.0	83.0	91.0	91.0	78.0	76.0	79.0	91.0	77.0	91.0	63.0	90.0	75.0	91.0	76.0	61.0	87.0	94.0	79.0	88.0	68.0	58.0	51.0	15.0	13.0	5.0	10.0	13.0	196.4M
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
18202	18202	19	England	47	65	60000.0	1000.0	1307	Right	1.0	2.0	2.0	Medium/ Medium	Lean	CM	22.0	May 3, 2017	2019	5'9	134lbs	42+2	42+2	42+2	44+2	44+2	44+2	44+2	44+2	45+2	45+2	45+2	44+2	45+2	45+2	45+2	44+2	44+2	45+2	45+2	45+2	44+2	45+2	45+2	45+2	45+2	45+2	34.0	38.0	40.0	49.0	25.0	42.0	30.0	34.0	45.0	43.0	54.0	57.0	60.0	49.0	76.0	43.0	55.0	40.0	47.0	38.0	46.0	46.0	39.0	52.0	43.0	45.0	40.0	48.0	47.0	10.0	13.0	7.0	8.0	9.0	143K
18203	18203	19	Sweden	47	63	60000.0	1000.0	1098	Right	1.0	2.0	2.0	Medium/ Medium	Normal	ST	21.0	Mar 19, 2018	2020	6'3	170lbs	45+2	45+2	45+2	39+2	42+2	42+2	42+2	39+2	40+2	40+2	40+2	38+2	35+2	35+2	35+2	38+2	30+2	31+2	31+2	31+2	30+2	29+2	32+2	32+2	32+2	29+2	23.0	52.0	52.0	43.0	36.0	39.0	32.0	20.0	25.0	40.0	41.0	39.0	38.0	40.0	52.0	41.0	47.0	43.0	67.0	42.0	47.0	16.0	46.0	33.0	43.0	42.0	22.0	15.0	19.0	10.0	9.0	9.0	5.0	12.0	113K
18204	18204	16	England	47	67	60000.0	1000.0	1189	Right	1.0	3.0	2.0	Medium/ Medium	Normal	ST	33.0	Jul 1, 2017	2021	5'8	148lbs	45+2	45+2	45+2	45+2	46+2	46+2	46+2	45+2	44+2	44+2	44+2	44+2	38+2	38+2	38+2	44+2	34+2	30+2	30+2	30+2	34+2	33+2	28+2	28+2	28+2	33+2	25.0	40.0	46.0	38.0	38.0	45.0	38.0	27.0	28.0	44.0	70.0	69.0	50.0	47.0	58.0	45.0	60.0	55.0	32.0	45.0	32.0	15.0	48.0	43.0	55.0	41.0	32.0	13.0	11.0	6.0	5.0	10.0	6.0	13.0	165K
18205	18205	17	England	47	66	60000.0	1000.0	1228	Right	1.0	3.0	2.0	Medium/ Medium	Lean	RW	34.0	Apr 24, 2018	2019	5'10	154lbs	47+2	47+2	47+2	47+2	46+2	46+2	46+2	47+2	45+2	45+2	45+2	46+2	39+2	39+2	39+2	46+2	36+2	32+2	32+2	32+2	36+2	35+2	31+2	31+2	31+2	35+2	44.0	50.0	39.0	42.0	40.0	51.0	34.0	32.0	32.0	52.0	61.0	60.0	52.0	21.0	71.0	64.0	42.0	40.0	48.0	34.0	33.0	22.0	44.0	47.0	50.0	46.0	20.0	25.0	27.0	14.0	6.0	14.0	8.0	9.0	143K
18206	18206	16	England	46	66	60000.0	1000.0	1321	Right	1.0	3.0	2.0	Medium/ Medium	Lean	CM	33.0	Oct 30, 2018	2019	5'10	176lbs	43+2	43+2	43+2	45+2	44+2	44+2	44+2	45+2	45+2	45+2	45+2	46+2	45+2	45+2	45+2	46+2	46+2	46+2	46+2	46+2	46+2	46+2	47+2	47+2	47+2	46+2	41.0	34.0	46.0	48.0	30.0	43.0	40.0	34.0	44.0	51.0	57.0	55.0	55.0	51.0	63.0	43.0	62.0	47.0	60.0	32.0	56.0	42.0	34.0	49.0	33.0	43.0	40.0	43.0	50.0	10.0	15.0	9.0	12.0	9.0	165K

18207 rows × 81 columns

In [32]:

fifa['Release Clause'] = fifa['Release Clause'].replace(repl_dict, regex=True)
new = fifa["Release Clause"].str.split("*", n = 1, expand = True)
fifa["Wage1"]= new[0] 
fifa["Wage2"]= new[1]
fifa['Wage1'] = pd.to_numeric(fifa['Wage1'], errors='coerce')
fifa['Wage2'] = pd.to_numeric(fifa['Wage2'], errors='coerce')
fifa['Release Clause'] = fifa['Wage1'] * fifa['Wage2']
fifa = fifa.drop(columns = ['Wage1', 'Wage2'])
fifa = fifa.dropna()

fifa

Out[32]:

	Unnamed: 0	Age	Nationality	Overall	Potential	Value	Wage	Special	Preferred Foot	International Reputation	Weak Foot	Skill Moves	Work Rate	Body Type	Position	Jersey Number	Joined	Contract Valid Until	Height	Weight	LS	ST	RS	LW	LF	CF	RF	RW	LAM	CAM	RAM	LM	LCM	CM	RCM	RM	LWB	LDM	CDM	RDM	RWB	LB	LCB	CB	RCB	RB	Crossing	Finishing	HeadingAccuracy	ShortPassing	Volleys	Dribbling	Curve	FKAccuracy	LongPassing	BallControl	Acceleration	SprintSpeed	Agility	Reactions	Balance	ShotPower	Jumping	Stamina	Strength	LongShots	Aggression	Interceptions	Positioning	Vision	Penalties	Composure	Marking	StandingTackle	SlidingTackle	GKDiving	GKHandling	GKKicking	GKPositioning	GKReflexes	Release Clause
0	0	31	Argentina	94	94	110500000.0	565000.0	2202	Left	5.0	4.0	4.0	Medium/ Medium	Messi	RF	10.0	Jul 1, 2004	2021	5'7	159lbs	88+2	88+2	88+2	92+2	93+2	93+2	93+2	92+2	93+2	93+2	93+2	91+2	84+2	84+2	84+2	91+2	64+2	61+2	61+2	61+2	64+2	59+2	47+2	47+2	47+2	59+2	84.0	95.0	70.0	90.0	86.0	97.0	93.0	94.0	87.0	96.0	91.0	86.0	91.0	95.0	95.0	85.0	68.0	72.0	59.0	94.0	48.0	22.0	94.0	94.0	75.0	96.0	33.0	28.0	26.0	6.0	11.0	15.0	14.0	8.0	226500000.0
1	1	33	Portugal	94	94	77000000.0	405000.0	2228	Right	5.0	4.0	5.0	High/ Low	C. Ronaldo	ST	7.0	Jul 10, 2018	2022	6'2	183lbs	91+3	91+3	91+3	89+3	90+3	90+3	90+3	89+3	88+3	88+3	88+3	88+3	81+3	81+3	81+3	88+3	65+3	61+3	61+3	61+3	65+3	61+3	53+3	53+3	53+3	61+3	84.0	94.0	89.0	81.0	87.0	88.0	81.0	76.0	77.0	94.0	89.0	91.0	87.0	96.0	70.0	95.0	95.0	88.0	79.0	93.0	63.0	29.0	95.0	82.0	85.0	95.0	28.0	31.0	23.0	7.0	11.0	15.0	14.0	11.0	127100000.0
2	2	26	Brazil	92	93	118500000.0	290000.0	2143	Right	5.0	5.0	5.0	High/ Medium	Neymar	LW	10.0	Aug 3, 2017	2022	5'9	150lbs	84+3	84+3	84+3	89+3	89+3	89+3	89+3	89+3	89+3	89+3	89+3	88+3	81+3	81+3	81+3	88+3	65+3	60+3	60+3	60+3	65+3	60+3	47+3	47+3	47+3	60+3	79.0	87.0	62.0	84.0	84.0	96.0	88.0	87.0	78.0	95.0	94.0	90.0	96.0	94.0	84.0	80.0	61.0	81.0	49.0	82.0	56.0	36.0	89.0	87.0	81.0	94.0	27.0	24.0	33.0	9.0	9.0	15.0	15.0	11.0	228100000.0
4	4	27	Belgium	91	92	102000000.0	355000.0	2281	Right	4.0	5.0	4.0	High/ High	Normal	RCM	7.0	Aug 30, 2015	2023	5'11	154lbs	82+3	82+3	82+3	87+3	87+3	87+3	87+3	87+3	88+3	88+3	88+3	88+3	87+3	87+3	87+3	88+3	77+3	77+3	77+3	77+3	77+3	73+3	66+3	66+3	66+3	73+3	93.0	82.0	55.0	92.0	82.0	86.0	85.0	83.0	91.0	91.0	78.0	76.0	79.0	91.0	77.0	91.0	63.0	90.0	75.0	91.0	76.0	61.0	87.0	94.0	79.0	88.0	68.0	58.0	51.0	15.0	13.0	5.0	10.0	13.0	196400000.0
5	5	27	Belgium	91	91	93000000.0	340000.0	2142	Right	4.0	4.0	4.0	High/ Medium	Normal	LF	10.0	Jul 1, 2012	2020	5'8	163lbs	83+3	83+3	83+3	89+3	88+3	88+3	88+3	89+3	89+3	89+3	89+3	89+3	82+3	82+3	82+3	89+3	66+3	63+3	63+3	63+3	66+3	60+3	49+3	49+3	49+3	60+3	81.0	84.0	61.0	89.0	80.0	95.0	83.0	79.0	83.0	94.0	94.0	88.0	95.0	90.0	94.0	82.0	56.0	83.0	66.0	80.0	54.0	41.0	87.0	89.0	86.0	91.0	34.0	27.0	22.0	11.0	12.0	6.0	8.0	8.0	172100000.0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
18202	18202	19	England	47	65	60000.0	1000.0	1307	Right	1.0	2.0	2.0	Medium/ Medium	Lean	CM	22.0	May 3, 2017	2019	5'9	134lbs	42+2	42+2	42+2	44+2	44+2	44+2	44+2	44+2	45+2	45+2	45+2	44+2	45+2	45+2	45+2	44+2	44+2	45+2	45+2	45+2	44+2	45+2	45+2	45+2	45+2	45+2	34.0	38.0	40.0	49.0	25.0	42.0	30.0	34.0	45.0	43.0	54.0	57.0	60.0	49.0	76.0	43.0	55.0	40.0	47.0	38.0	46.0	46.0	39.0	52.0	43.0	45.0	40.0	48.0	47.0	10.0	13.0	7.0	8.0	9.0	143000.0
18203	18203	19	Sweden	47	63	60000.0	1000.0	1098	Right	1.0	2.0	2.0	Medium/ Medium	Normal	ST	21.0	Mar 19, 2018	2020	6'3	170lbs	45+2	45+2	45+2	39+2	42+2	42+2	42+2	39+2	40+2	40+2	40+2	38+2	35+2	35+2	35+2	38+2	30+2	31+2	31+2	31+2	30+2	29+2	32+2	32+2	32+2	29+2	23.0	52.0	52.0	43.0	36.0	39.0	32.0	20.0	25.0	40.0	41.0	39.0	38.0	40.0	52.0	41.0	47.0	43.0	67.0	42.0	47.0	16.0	46.0	33.0	43.0	42.0	22.0	15.0	19.0	10.0	9.0	9.0	5.0	12.0	113000.0
18204	18204	16	England	47	67	60000.0	1000.0	1189	Right	1.0	3.0	2.0	Medium/ Medium	Normal	ST	33.0	Jul 1, 2017	2021	5'8	148lbs	45+2	45+2	45+2	45+2	46+2	46+2	46+2	45+2	44+2	44+2	44+2	44+2	38+2	38+2	38+2	44+2	34+2	30+2	30+2	30+2	34+2	33+2	28+2	28+2	28+2	33+2	25.0	40.0	46.0	38.0	38.0	45.0	38.0	27.0	28.0	44.0	70.0	69.0	50.0	47.0	58.0	45.0	60.0	55.0	32.0	45.0	32.0	15.0	48.0	43.0	55.0	41.0	32.0	13.0	11.0	6.0	5.0	10.0	6.0	13.0	165000.0
18205	18205	17	England	47	66	60000.0	1000.0	1228	Right	1.0	3.0	2.0	Medium/ Medium	Lean	RW	34.0	Apr 24, 2018	2019	5'10	154lbs	47+2	47+2	47+2	47+2	46+2	46+2	46+2	47+2	45+2	45+2	45+2	46+2	39+2	39+2	39+2	46+2	36+2	32+2	32+2	32+2	36+2	35+2	31+2	31+2	31+2	35+2	44.0	50.0	39.0	42.0	40.0	51.0	34.0	32.0	32.0	52.0	61.0	60.0	52.0	21.0	71.0	64.0	42.0	40.0	48.0	34.0	33.0	22.0	44.0	47.0	50.0	46.0	20.0	25.0	27.0	14.0	6.0	14.0	8.0	9.0	143000.0
18206	18206	16	England	46	66	60000.0	1000.0	1321	Right	1.0	3.0	2.0	Medium/ Medium	Lean	CM	33.0	Oct 30, 2018	2019	5'10	176lbs	43+2	43+2	43+2	45+2	44+2	44+2	44+2	45+2	45+2	45+2	45+2	46+2	45+2	45+2	45+2	46+2	46+2	46+2	46+2	46+2	46+2	46+2	47+2	47+2	47+2	46+2	41.0	34.0	46.0	48.0	30.0	43.0	40.0	34.0	44.0	51.0	57.0	55.0	55.0	51.0	63.0	43.0	62.0	47.0	60.0	32.0	56.0	42.0	34.0	49.0	33.0	43.0	40.0	43.0	50.0	10.0	15.0	9.0	12.0	9.0	165000.0

14743 rows × 81 columns

In [33]:

fifa.LS = fifa.LS.apply(lambda x: pd.Series(str(x).split("+")))
fifa.ST = fifa.ST.apply(lambda x: pd.Series(str(x).split("+")))
fifa.RS = fifa.RS.apply(lambda x: pd.Series(str(x).split("+")))
fifa.LW = fifa.LW.apply(lambda x: pd.Series(str(x).split("+")))
fifa.LF = fifa.LF.apply(lambda x: pd.Series(str(x).split("+")))
fifa.CF = fifa.CF.apply(lambda x: pd.Series(str(x).split("+")))
fifa.RF = fifa.RF.apply(lambda x: pd.Series(str(x).split("+")))
fifa.RW = fifa.RW.apply(lambda x: pd.Series(str(x).split("+")))
fifa.LAM = fifa.LAM.apply(lambda x: pd.Series(str(x).split("+")))
fifa.CAM = fifa.CAM.apply(lambda x: pd.Series(str(x).split("+")))
fifa.RAM = fifa.RAM.apply(lambda x: pd.Series(str(x).split("+")))
fifa.RM = fifa.RM.apply(lambda x: pd.Series(str(x).split("+")))
fifa.LM = fifa.LM.apply(lambda x: pd.Series(str(x).split("+")))
fifa.CM = fifa.CM.apply(lambda x: pd.Series(str(x).split("+")))
fifa.RCM = fifa.RCM.apply(lambda x: pd.Series(str(x).split("+")))
fifa.LCM = fifa.LCM.apply(lambda x: pd.Series(str(x).split("+")))
fifa.LWB = fifa.LWB.apply(lambda x: pd.Series(str(x).split("+")))
fifa.LDM = fifa.LDM.apply(lambda x: pd.Series(str(x).split("+")))
fifa.CDM = fifa.CDM.apply(lambda x: pd.Series(str(x).split("+")))
fifa.RDM = fifa.RDM.apply(lambda x: pd.Series(str(x).split("+")))
fifa.RWB = fifa.RWB.apply(lambda x: pd.Series(str(x).split("+")))
fifa.LB = fifa.LB.apply(lambda x: pd.Series(str(x).split("+")))
fifa.LCB = fifa.LCB.apply(lambda x: pd.Series(str(x).split("+")))
fifa.CB = fifa.CB.apply(lambda x: pd.Series(str(x).split("+")))
fifa.RCB = fifa.RCB.apply(lambda x: pd.Series(str(x).split("+")))
fifa.RB = fifa.RB.apply(lambda x: pd.Series(str(x).split("+")))

fifa

Out[33]:

	Unnamed: 0	Age	Nationality	Overall	Potential	Value	Wage	Special	Preferred Foot	International Reputation	Weak Foot	Skill Moves	Work Rate	Body Type	Position	Jersey Number	Joined	Contract Valid Until	Height	Weight	LS	ST	RS	LW	LF	CF	RF	RW	LAM	CAM	RAM	LM	LCM	CM	RCM	RM	LWB	LDM	CDM	RDM	RWB	LB	LCB	CB	RCB	RB	Crossing	Finishing	HeadingAccuracy	ShortPassing	Volleys	Dribbling	Curve	FKAccuracy	LongPassing	BallControl	Acceleration	SprintSpeed	Agility	Reactions	Balance	ShotPower	Jumping	Stamina	Strength	LongShots	Aggression	Interceptions	Positioning	Vision	Penalties	Composure	Marking	StandingTackle	SlidingTackle	GKDiving	GKHandling	GKKicking	GKPositioning	GKReflexes	Release Clause
0	0	31	Argentina	94	94	110500000.0	565000.0	2202	Left	5.0	4.0	4.0	Medium/ Medium	Messi	RF	10.0	Jul 1, 2004	2021	5'7	159lbs	88	88	88	92	93	93	93	92	93	93	93	91	84	84	84	91	64	61	61	61	64	59	47	47	47	59	84.0	95.0	70.0	90.0	86.0	97.0	93.0	94.0	87.0	96.0	91.0	86.0	91.0	95.0	95.0	85.0	68.0	72.0	59.0	94.0	48.0	22.0	94.0	94.0	75.0	96.0	33.0	28.0	26.0	6.0	11.0	15.0	14.0	8.0	226500000.0
1	1	33	Portugal	94	94	77000000.0	405000.0	2228	Right	5.0	4.0	5.0	High/ Low	C. Ronaldo	ST	7.0	Jul 10, 2018	2022	6'2	183lbs	91	91	91	89	90	90	90	89	88	88	88	88	81	81	81	88	65	61	61	61	65	61	53	53	53	61	84.0	94.0	89.0	81.0	87.0	88.0	81.0	76.0	77.0	94.0	89.0	91.0	87.0	96.0	70.0	95.0	95.0	88.0	79.0	93.0	63.0	29.0	95.0	82.0	85.0	95.0	28.0	31.0	23.0	7.0	11.0	15.0	14.0	11.0	127100000.0
2	2	26	Brazil	92	93	118500000.0	290000.0	2143	Right	5.0	5.0	5.0	High/ Medium	Neymar	LW	10.0	Aug 3, 2017	2022	5'9	150lbs	84	84	84	89	89	89	89	89	89	89	89	88	81	81	81	88	65	60	60	60	65	60	47	47	47	60	79.0	87.0	62.0	84.0	84.0	96.0	88.0	87.0	78.0	95.0	94.0	90.0	96.0	94.0	84.0	80.0	61.0	81.0	49.0	82.0	56.0	36.0	89.0	87.0	81.0	94.0	27.0	24.0	33.0	9.0	9.0	15.0	15.0	11.0	228100000.0
4	4	27	Belgium	91	92	102000000.0	355000.0	2281	Right	4.0	5.0	4.0	High/ High	Normal	RCM	7.0	Aug 30, 2015	2023	5'11	154lbs	82	82	82	87	87	87	87	87	88	88	88	88	87	87	87	88	77	77	77	77	77	73	66	66	66	73	93.0	82.0	55.0	92.0	82.0	86.0	85.0	83.0	91.0	91.0	78.0	76.0	79.0	91.0	77.0	91.0	63.0	90.0	75.0	91.0	76.0	61.0	87.0	94.0	79.0	88.0	68.0	58.0	51.0	15.0	13.0	5.0	10.0	13.0	196400000.0
5	5	27	Belgium	91	91	93000000.0	340000.0	2142	Right	4.0	4.0	4.0	High/ Medium	Normal	LF	10.0	Jul 1, 2012	2020	5'8	163lbs	83	83	83	89	88	88	88	89	89	89	89	89	82	82	82	89	66	63	63	63	66	60	49	49	49	60	81.0	84.0	61.0	89.0	80.0	95.0	83.0	79.0	83.0	94.0	94.0	88.0	95.0	90.0	94.0	82.0	56.0	83.0	66.0	80.0	54.0	41.0	87.0	89.0	86.0	91.0	34.0	27.0	22.0	11.0	12.0	6.0	8.0	8.0	172100000.0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
18202	18202	19	England	47	65	60000.0	1000.0	1307	Right	1.0	2.0	2.0	Medium/ Medium	Lean	CM	22.0	May 3, 2017	2019	5'9	134lbs	42	42	42	44	44	44	44	44	45	45	45	44	45	45	45	44	44	45	45	45	44	45	45	45	45	45	34.0	38.0	40.0	49.0	25.0	42.0	30.0	34.0	45.0	43.0	54.0	57.0	60.0	49.0	76.0	43.0	55.0	40.0	47.0	38.0	46.0	46.0	39.0	52.0	43.0	45.0	40.0	48.0	47.0	10.0	13.0	7.0	8.0	9.0	143000.0
18203	18203	19	Sweden	47	63	60000.0	1000.0	1098	Right	1.0	2.0	2.0	Medium/ Medium	Normal	ST	21.0	Mar 19, 2018	2020	6'3	170lbs	45	45	45	39	42	42	42	39	40	40	40	38	35	35	35	38	30	31	31	31	30	29	32	32	32	29	23.0	52.0	52.0	43.0	36.0	39.0	32.0	20.0	25.0	40.0	41.0	39.0	38.0	40.0	52.0	41.0	47.0	43.0	67.0	42.0	47.0	16.0	46.0	33.0	43.0	42.0	22.0	15.0	19.0	10.0	9.0	9.0	5.0	12.0	113000.0
18204	18204	16	England	47	67	60000.0	1000.0	1189	Right	1.0	3.0	2.0	Medium/ Medium	Normal	ST	33.0	Jul 1, 2017	2021	5'8	148lbs	45	45	45	45	46	46	46	45	44	44	44	44	38	38	38	44	34	30	30	30	34	33	28	28	28	33	25.0	40.0	46.0	38.0	38.0	45.0	38.0	27.0	28.0	44.0	70.0	69.0	50.0	47.0	58.0	45.0	60.0	55.0	32.0	45.0	32.0	15.0	48.0	43.0	55.0	41.0	32.0	13.0	11.0	6.0	5.0	10.0	6.0	13.0	165000.0
18205	18205	17	England	47	66	60000.0	1000.0	1228	Right	1.0	3.0	2.0	Medium/ Medium	Lean	RW	34.0	Apr 24, 2018	2019	5'10	154lbs	47	47	47	47	46	46	46	47	45	45	45	46	39	39	39	46	36	32	32	32	36	35	31	31	31	35	44.0	50.0	39.0	42.0	40.0	51.0	34.0	32.0	32.0	52.0	61.0	60.0	52.0	21.0	71.0	64.0	42.0	40.0	48.0	34.0	33.0	22.0	44.0	47.0	50.0	46.0	20.0	25.0	27.0	14.0	6.0	14.0	8.0	9.0	143000.0
18206	18206	16	England	46	66	60000.0	1000.0	1321	Right	1.0	3.0	2.0	Medium/ Medium	Lean	CM	33.0	Oct 30, 2018	2019	5'10	176lbs	43	43	43	45	44	44	44	45	45	45	45	46	45	45	45	46	46	46	46	46	46	46	47	47	47	46	41.0	34.0	46.0	48.0	30.0	43.0	40.0	34.0	44.0	51.0	57.0	55.0	55.0	51.0	63.0	43.0	62.0	47.0	60.0	32.0	56.0	42.0	34.0	49.0	33.0	43.0	40.0	43.0	50.0	10.0	15.0	9.0	12.0	9.0	165000.0

14743 rows × 81 columns

Exploratory Analysis¶

In [34]:

fifa["Nationality"].value_counts().head(10).plot(kind = 'bar', figsize = [15,5])
plt.show()

In [35]:

fifa["Value"].value_counts().plot(kind = 'hist', figsize = [15,8])
plt.show()

In [35]:

Data Modeling using Pycaret¶

In [37]:

from sklearn.model_selection import train_test_split
train, test = train_test_split(fifa, test_size = 0.9, random_state=42)
train

Out[37]:

	Unnamed: 0	Age	Nationality	Overall	Potential	Value	Wage	Special	Preferred Foot	International Reputation	Weak Foot	Skill Moves	Work Rate	Body Type	Position	Jersey Number	Joined	Contract Valid Until	Height	Weight	LS	ST	RS	LW	LF	CF	RF	RW	LAM	CAM	RAM	LM	LCM	CM	RCM	RM	LWB	LDM	CDM	RDM	RWB	LB	LCB	CB	RCB	RB	Crossing	Finishing	HeadingAccuracy	ShortPassing	Volleys	Dribbling	Curve	FKAccuracy	LongPassing	BallControl	Acceleration	SprintSpeed	Agility	Reactions	Balance	ShotPower	Jumping	Stamina	Strength	LongShots	Aggression	Interceptions	Positioning	Vision	Penalties	Composure	Marking	StandingTackle	SlidingTackle	GKDiving	GKHandling	GKKicking	GKPositioning	GKReflexes	Release Clause
15998	15998	21	France	58	65	150000.0	3000.0	1464	Right	1.0	2.0	2.0	Medium/ Medium	Normal	RB	35.0	Jul 12, 2017	2019	5'11	174lbs	48	48	48	50	49	49	49	50	49	49	49	52	50	50	50	52	57	54	54	54	57	57	56	56	56	57	56.0	36.0	48.0	52.0	35.0	53.0	31.0	36.0	47.0	52.0	64.0	61.0	52.0	54.0	57.0	44.0	56.0	62.0	61.0	41.0	58.0	58.0	49.0	39.0	40.0	45.0	51.0	63.0	60.0	8.0	13.0	9.0	9.0	9.0	315000.0
6032	6032	18	Germany	69	88	2200000.0	4000.0	1547	Right	1.0	3.0	3.0	Medium/ Medium	Lean	ST	15.0	Jul 1, 2017	2020	6'0	172lbs	68	68	68	64	67	67	67	64	63	63	63	61	53	53	53	61	42	39	39	39	42	40	36	36	36	40	36.0	74.0	63.0	50.0	65.0	69.0	39.0	38.0	34.0	69.0	71.0	68.0	80.0	73.0	71.0	66.0	59.0	57.0	65.0	58.0	31.0	16.0	74.0	57.0	55.0	58.0	18.0	17.0	20.0	14.0	12.0	10.0	7.0	11.0	4900000.0
17678	17678	19	England	53	60	80000.0	1000.0	1425	Left	1.0	3.0	2.0	Medium/ Medium	Lean	ST	21.0	Mar 31, 2016	2020	5'9	137lbs	51	51	51	52	51	51	51	52	49	49	49	50	45	45	45	50	48	45	45	45	48	48	46	46	46	48	46.0	57.0	40.0	43.0	33.0	54.0	32.0	29.0	32.0	52.0	59.0	63.0	69.0	57.0	74.0	46.0	65.0	50.0	54.0	40.0	52.0	54.0	56.0	38.0	55.0	40.0	37.0	42.0	41.0	12.0	14.0	9.0	10.0	10.0	156000.0
16217	16217	20	Germany	58	71	250000.0	3000.0	1419	Left	1.0	3.0	3.0	Medium/ Medium	Lean	RM	16.0	Jul 1, 2017	2019	5'9	152lbs	51	51	51	57	54	54	54	57	55	55	55	56	50	50	50	56	43	40	40	40	43	41	34	34	34	41	55.0	51.0	40.0	54.0	50.0	67.0	57.0	47.0	51.0	60.0	68.0	67.0	78.0	46.0	76.0	45.0	34.0	45.0	44.0	44.0	38.0	21.0	47.0	52.0	53.0	50.0	23.0	30.0	25.0	13.0	10.0	8.0	13.0	7.0	606000.0
8279	8279	18	Netherlands	67	79	1300000.0	9000.0	1673	Right	1.0	3.0	3.0	Medium/ Medium	Lean	CAM	71.0	Jul 14, 2018	2022	5'8	141lbs	60	60	60	65	64	64	64	65	65	65	65	65	61	61	61	65	53	50	50	50	53	49	41	41	41	49	64.0	58.0	42.0	64.0	60.0	72.0	70.0	64.0	57.0	70.0	72.0	72.0	68.0	62.0	81.0	64.0	60.0	66.0	54.0	60.0	39.0	36.0	52.0	72.0	52.0	54.0	35.0	29.0	28.0	10.0	13.0	11.0	11.0	5.0	2600000.0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
6303	6303	30	Spain	69	69	775000.0	5000.0	1890	Right	1.0	3.0	3.0	Medium/ High	Lean	LDM	6.0	Aug 16, 2016	2020	6'0	154lbs	63	63	63	64	64	64	64	64	65	65	65	65	67	67	67	65	66	68	68	68	66	66	66	66	66	66	58.0	49.0	57.0	69.0	66.0	66.0	71.0	56.0	66.0	70.0	68.0	67.0	62.0	71.0	69.0	75.0	75.0	73.0	72.0	68.0	72.0	73.0	58.0	66.0	53.0	60.0	55.0	69.0	62.0	8.0	14.0	12.0	6.0	14.0	1200000.0
16473	16473	19	Mexico	57	71	200000.0	1000.0	1436	Right	1.0	2.0	2.0	Medium/ Medium	Normal	RB	35.0	Jul 1, 2018	2021	5'9	170lbs	45	45	45	48	47	47	47	48	47	47	47	50	48	48	48	50	55	53	53	53	55	56	56	56	56	56	45.0	31.0	53.0	53.0	29.0	62.0	36.0	41.0	47.0	40.0	69.0	54.0	53.0	55.0	68.0	31.0	56.0	62.0	57.0	28.0	54.0	54.0	49.0	37.0	45.0	38.0	49.0	67.0	64.0	13.0	5.0	8.0	13.0	8.0	465000.0
6559	6559	18	Spain	69	86	2200000.0	24000.0	1628	Right	1.0	5.0	4.0	Medium/ Medium	Normal	LW	55.0	Aug 31, 2016	2019	5'7	150lbs	62	62	62	68	68	68	68	68	68	68	68	67	60	60	60	67	50	46	46	46	50	45	37	37	37	45	53.0	66.0	30.0	71.0	44.0	76.0	62.0	47.0	50.0	74.0	78.0	71.0	81.0	61.0	84.0	70.0	65.0	58.0	38.0	63.0	41.0	20.0	65.0	64.0	58.0	62.0	43.0	23.0	21.0	13.0	9.0	13.0	10.0	6.0	5400000.0
1016	1016	21	Germany	77	84	11000000.0	22000.0	1795	Right	1.0	3.0	3.0	Medium/ Medium	Lean	RCB	31.0	May 15, 2015	2021	6'2	165lbs	60	60	60	59	61	61	61	59	62	62	62	62	66	66	66	62	69	73	73	73	69	71	76	76	76	71	42.0	42.0	74.0	71.0	38.0	66.0	37.0	39.0	69.0	70.0	54.0	73.0	62.0	75.0	56.0	55.0	71.0	72.0	78.0	45.0	76.0	78.0	52.0	57.0	48.0	72.0	79.0	79.0	76.0	11.0	12.0	12.0	13.0	13.0	22000000.0
8852	8852	25	Germany	66	70	675000.0	1000.0	1699	Right	1.0	3.0	3.0	High/ Medium	Lean	RB	27.0	Jul 1, 2017	2019	5'8	161lbs	52	52	52	60	57	57	57	60	59	59	59	62	58	58	58	62	65	61	61	61	65	65	60	60	60	65	65.0	33.0	45.0	62.0	42.0	70.0	44.0	34.0	51.0	66.0	79.0	75.0	77.0	57.0	82.0	49.0	73.0	74.0	49.0	44.0	66.0	62.0	51.0	52.0	41.0	55.0	59.0	64.0	69.0	12.0	14.0	14.0	10.0	14.0	1000000.0

1474 rows × 81 columns

Setting up a pycaret session

In [38]:

session_1 = setup(train, target = 'Value', session_id=1, log_experiment=False, experiment_name='Cases_1')
# , pca = True, pca_method='linear'

 
Setup Succesfully Completed.

	Description	Value
0	session_id	1
1	Transform Target	False
2	Transform Target Method	None
3	Original Data	(1474, 81)
4	Missing Values	False
5	Numeric Features	71
6	Categorical Features	8
7	Ordinal Features	False
8	High Cardinality Features	False
9	High Cardinality Method	None
10	Sampled Data	(1474, 81)
11	Transformed Train Set	(1031, 312)
12	Transformed Test Set	(443, 312)
13	Numeric Imputer	mean
14	Categorical Imputer	constant
15	Normalize	False
16	Normalize Method	None
17	Transformation	False
18	Transformation Method	None
19	PCA	False
20	PCA Method	None
21	PCA Components	None
22	Ignore Low Variance	False
23	Combine Rare Levels	False
24	Rare Level Threshold	None
25	Numeric Binning	False
26	Remove Outliers	False
27	Outliers Threshold	None
28	Remove Multicollinearity	False
29	Multicollinearity Threshold	None
30	Clustering	False
31	Clustering Iteration	None
32	Polynomial Features	False
33	Polynomial Degree	None
34	Trignometry Features	False
35	Polynomial Threshold	None
36	Group Features	False
37	Feature Selection	False
38	Features Selection Threshold	None
39	Feature Interaction	False
40	Feature Ratio	False
41	Interaction Threshold	None

In [39]:

best_model = compare_models()

	Model	MAE	MSE	RMSE	R2	RMSLE	MAPE	TT (Sec)
0	Lasso Least Angle Regression	282783.0442	423761074666.3661	618255.7624	0.9794	0.5431	0.3628	0.0554
1	Gradient Boosting Regressor	249016.2020	697890264418.2385	718749.2301	0.9793	0.1910	0.1494	1.3029
2	Elastic Net	321864.4501	439091653534.2890	634103.3412	0.9787	0.6109	0.5726	0.2823
3	Huber Regressor	272589.6630	441193740635.0476	643752.9687	0.9786	0.2102	0.1589	0.1302
4	Bayesian Ridge	270370.4972	451737756385.2668	636500.0104	0.9784	0.4566	0.2395	0.1347
5	Extreme Gradient Boosting	267334.9126	663289327027.7209	752380.4902	0.9778	0.2164	0.1699	0.5436
6	TheilSen Regressor	363298.5789	467526227166.3256	661961.4975	0.9777	0.7542	0.6181	539.9337
7	Ridge Regression	376534.7130	451663765364.9515	647883.3563	0.9777	0.7450	0.7241	0.0197
8	Orthogonal Matching Pursuit	321516.2408	474298331234.1436	660397.7113	0.9761	0.5408	0.4595	0.0211
9	Lasso Regression	391584.6039	496889428240.3161	683211.5390	0.9748	0.7241	0.7383	0.3531
10	Linear Regression	401123.0674	499013888281.1590	685450.5461	0.9746	0.6867	0.7735	0.0490
11	Extra Trees Regressor	242228.1600	1273580457742.6252	892912.1996	0.9648	0.1252	0.0934	2.3143
12	Random Forest	284029.1127	1515355955273.2683	1008251.6042	0.9632	0.1317	0.1048	2.6496
13	CatBoost Regressor	279535.2383	1850800579453.9272	1010098.9721	0.9629	0.3135	0.1640	7.0155
14	K Neighbors Regressor	345007.0948	2102487415982.0759	1166314.1061	0.9488	0.1826	0.1489	0.0260
15	Passive Aggressive Regressor	408370.6432	1261604319312.5366	1042123.1443	0.9391	0.2455	0.1952	0.0256
16	Decision Tree	409796.3032	2187238335511.5757	1345973.7968	0.9294	0.1842	0.1437	0.0675
17	AdaBoost Regressor	718681.0211	2563097796765.3745	1390477.9733	0.9277	1.0277	1.8889	0.5268
18	Light Gradient Boosting Machine	435781.1752	3666142106110.5806	1583551.9247	0.9138	0.2488	0.1447	0.3356
19	Random Sample Consensus	405678.3472	2767493507852.2100	1122299.7747	0.8165	0.5970	0.8472	3.3608
20	Support Vector Machine	2087378.6090	33234606101056.3633	5436038.1265	-0.1267	1.3826	1.3679	0.4923
21	Least Angle Regression	28477922902607237878544330716293095344832512.0000	455478406000872500511301671368618166157698670765252318388099071450535744244678880210714624.0000	213419400773072811771872404793673993099935744.0000	-22339438705739811992478101946947357107486588606143416563650532566228048805888.0000	20.4804	47376671302580016906739564486764527616.0000	0.5740

In [40]:

model_metadata = models()
model_metadata['Name']

Out[40]:

ID
lr                          Linear Regression
lasso                        Lasso Regression
ridge                        Ridge Regression
en                                Elastic Net
lar                    Least Angle Regression
llar             Lasso Least Angle Regression
omp               Orthogonal Matching Pursuit
br                             Bayesian Ridge
ard         Automatic Relevance Determination
par              Passive Aggressive Regressor
ransac                Random Sample Consensus
tr                         TheilSen Regressor
huber                         Huber Regressor
kr                               Kernel Ridge
svm                    Support Vector Machine
knn                     K Neighbors Regressor
dt                              Decision Tree
rf                              Random Forest
et                      Extra Trees Regressor
ada                        AdaBoost Regressor
gbr               Gradient Boosting Regressor
mlp                    Multi Level Perceptron
xgboost             Extreme Gradient Boosting
lightgbm      Light Gradient Boosting Machine
catboost                   CatBoost Regressor
Name: Name, dtype: object

In [58]:

llar  = create_model('llar')

	MAE	MSE	RMSE	R2	RMSLE	MAPE
0	242943.5319	317938532908.5282	563860.3842	0.9899	0.5490	0.3871
1	272474.3952	255396296253.6623	505367.4863	0.9955	0.4174	0.4260
2	299320.0049	384062866058.8424	619728.0582	0.9951	0.6462	0.4325
3	233591.5346	163123816830.0286	403885.8958	0.9920	0.6024	0.4074
4	310272.4685	757208717093.8486	870177.4055	0.9405	0.4307	0.1767
5	239171.0924	288630406424.4498	537243.3400	0.9691	0.8464	0.3859
6	392617.9219	1191661077892.1279	1091632.2998	0.9648	0.4253	0.4027
7	257183.3933	168887542836.5881	410959.2958	0.9782	0.5327	0.3221
8	275441.9692	253692864859.1576	503679.3274	0.9822	0.3591	0.3421
9	304814.1295	457008625506.4266	676024.1309	0.9871	0.6219	0.3450
Mean	282783.0442	423761074666.3661	618255.7624	0.9794	0.5431	0.3628
SD	45058.5220	303835480554.6078	203766.7464	0.0164	0.1373	0.0711

In [59]:

gbr  = create_model('gbr')

	MAE	MSE	RMSE	R2	RMSLE	MAPE
0	235734.6989	437268521792.1236	661262.8235	0.9861	0.2263	0.1735
1	239582.3790	246721789834.1528	496710.9721	0.9957	0.1793	0.1368
2	344322.7507	3366666462331.4697	1834847.8036	0.9569	0.1705	0.1361
3	247847.7778	910555587931.8813	954230.3642	0.9553	0.1938	0.1402
4	260095.0887	366795816073.5381	605636.7030	0.9712	0.1674	0.1311
5	165263.0013	95822971602.6585	309552.8575	0.9897	0.1760	0.1331
6	272568.9045	614652691055.9829	783997.8897	0.9818	0.1845	0.1447
7	179339.0986	112536689841.8306	335464.8862	0.9855	0.1773	0.1449
8	208126.7229	143081559525.7167	378261.2319	0.9900	0.1910	0.1550
9	337281.5981	684800554193.0310	827526.7695	0.9806	0.2443	0.1986
Mean	249016.2020	697890264418.2385	718749.2301	0.9793	0.1910	0.1494
SD	55999.8190	925674322793.4565	425781.4094	0.0131	0.0238	0.0202

In [60]:

en  = create_model('en')

	MAE	MSE	RMSE	R2	RMSLE	MAPE
0	314520.8248	372394275396.3943	610241.1617	0.9882	0.6919	0.6782
1	313363.3779	279816560903.9476	528976.9002	0.9951	0.6625	0.7353
2	294572.0500	356054391770.7558	596702.9343	0.9954	0.8665	0.4919
3	289293.1310	302410799111.7908	549918.9023	0.9852	0.6134	0.6220
4	359663.1823	823463360870.0308	907448.8200	0.9353	0.3746	0.3215
5	277214.4139	242500630821.6496	492443.5306	0.9740	0.3776	0.4259
6	431248.4753	1145975018672.9460	1070502.2273	0.9661	0.6403	0.6521
7	270836.6835	171228571957.6938	413797.7428	0.9779	0.5140	0.4214
8	324672.5398	259930162773.1474	509833.4657	0.9817	0.7563	0.6482
9	343259.8229	437142763064.5327	661167.7269	0.9876	0.6120	0.7298
Mean	321864.4501	439091653534.2890	634103.3412	0.9787	0.6109	0.5726
SD	45153.8239	290744034870.6052	192365.8136	0.0168	0.1471	0.1381

In [61]:

tuned_llar = tune_model(llar)

	MAE	MSE	RMSE	R2	RMSLE	MAPE
0	289979.0259	322089950804.6690	567529.6916	0.9898	0.4839	0.5108
1	232743.8326	227522353294.4826	476993.0328	0.9960	0.3679	0.2513
2	251980.3530	365312028384.2730	604410.4800	0.9953	0.3774	0.2472
3	239734.2039	169203004572.4914	411342.9282	0.9917	0.6680	0.4263
4	309129.0897	755943408649.7677	869450.0610	0.9406	0.3532	0.1796
5	300644.1337	358718738645.5584	598931.3305	0.9616	0.6977	0.5089
6	387895.1744	1185057819017.0984	1088603.6097	0.9650	0.3973	0.3048
7	288825.5266	183906942546.0412	428843.7274	0.9763	0.5001	0.4076
8	319896.7195	290853935709.5784	539308.7573	0.9796	0.6416	0.4787
9	368209.4311	521650478342.3383	722253.7493	0.9852	0.5062	0.6609
Mean	298903.7490	438025865996.6299	630766.7368	0.9781	0.4993	0.3976
SD	48510.0388	298990451622.5987	200397.5793	0.0169	0.1234	0.1422

In [62]:

tuned_gbr = tune_model(gbr)

	MAE	MSE	RMSE	R2	RMSLE	MAPE
0	558122.9387	5272560990477.8496	2296205.7814	0.8323	0.2633	0.2076
1	739998.4752	7569379251828.7100	2751250.4887	0.8679	0.2870	0.2096
2	831756.5941	13798195187051.3418	3714592.1966	0.8234	0.2634	0.1865
3	340452.8458	908205269923.9082	952998.0430	0.9555	0.2754	0.1924
4	674109.4217	3846016468705.2871	1961126.3266	0.6976	0.3031	0.2124
5	395772.3860	819668446328.4290	905355.4254	0.9121	0.3706	0.2376
6	561391.2692	2465924916451.6304	1570326.3726	0.9271	0.3657	0.1839
7	299570.2771	316935959481.7112	562970.6560	0.9591	0.2940	0.1957
8	396341.8760	1207542097136.1785	1098882.2035	0.9152	0.2352	0.1916
9	882730.1880	12974755653040.2793	3602048.8133	0.6325	0.3279	0.2408
Mean	568024.6272	4917918424042.5332	1941575.6307	0.8523	0.2986	0.2058
SD	198133.1948	4752879000575.7910	1071542.1104	0.1044	0.0421	0.0191

In [63]:

tuned_en = tune_model(en)

	MAE	MSE	RMSE	R2	RMSLE	MAPE
0	313386.9529	369029649933.3783	607478.1065	0.9883	0.6378	0.6914
1	314569.0319	279983556880.9034	529134.7247	0.9951	0.6247	0.7503
2	292879.1641	354436751713.6628	595345.9093	0.9955	0.7697	0.4970
3	290623.1410	300547186625.9410	548221.8407	0.9853	0.6245	0.6329
4	359787.9423	814824678870.1437	902676.3976	0.9359	0.4036	0.3250
5	278805.5993	241523530453.4208	491450.4354	0.9741	0.3844	0.4314
6	431369.8737	1139086954764.6711	1067280.1669	0.9663	0.6725	0.6736
7	272358.7211	171746519052.9784	414423.1160	0.9779	0.4813	0.4294
8	324856.6863	261958193571.1935	511818.5162	0.9816	0.7129	0.6533
9	345653.6038	438950557480.9849	662533.4388	0.9876	0.5609	0.7611
Mean	322429.0716	437208757934.7278	633036.2652	0.9788	0.5872	0.5845
SD	44997.1749	288027990711.2840	190981.2683	0.0167	0.1219	0.1441

In [64]:

plot_model(tuned_en)

In [65]:

plot_model(tuned_en, plot = 'error')

In [66]:

plot_model(tuned_en, plot='feature')

In [67]:

evaluate_model(tuned_gbr)

interactive(children=(ToggleButtons(description='Plot Type:', icons=('',), options=(('Hyperparameters', 'param…

In [68]:

evaluate_model(tuned_en)

interactive(children=(ToggleButtons(description='Plot Type:', icons=('',), options=(('Hyperparameters', 'param…

In [69]:

evaluate_model(tuned_llar)

interactive(children=(ToggleButtons(description='Plot Type:', icons=('',), options=(('Hyperparameters', 'param…

In [70]:

blend = blend_models(estimator_list = [tuned_llar, tuned_gbr, tuned_en])

	MAE	MSE	RMSE	R2	RMSLE	MAPE
0	298124.0824	611464768604.9042	781962.1273	0.9806	0.5947	0.3850
1	338157.1802	757889217295.3031	870568.3301	0.9868	0.4962	0.3490
2	380954.5559	1594002809665.1304	1262538.2409	0.9796	0.4179	0.2603
3	275082.5747	333937002788.1300	577872.8258	0.9836	0.5529	0.4655
4	318669.4518	599903488246.2401	774534.3687	0.9528	0.3643	0.1977
5	279616.8154	260830511409.8741	510715.6855	0.9720	0.5768	0.3315
6	315413.1655	596632593213.6093	772419.9591	0.9824	0.4040	0.3430
7	240057.2984	171721535478.8066	414392.9723	0.9779	0.3392	0.2769
8	283373.2155	350993014683.1928	592446.6345	0.9753	0.3539	0.3814
9	467484.1193	2111686762935.4600	1453164.3964	0.9402	0.4916	0.4367
Mean	319693.2459	738906170432.0651	801061.5540	0.9731	0.4591	0.3427
SD	61382.2974	594694324001.8995	311779.6611	0.0142	0.0909	0.0771

In [71]:

pred = predict_model(blend);

	Model	MAE	MSE	RMSE	R2	RMSLE	MAPE
0	Voting Regressor	312303.2999	9.819626e+11	990940.2462	0.9719	0.4618	0.3341

In [72]:

final_blend = finalize_model(blend)

In [73]:

plot_model(final_blend)

In [74]:

plot_model(final_blend, plot = 'error')

In [75]:

save_model(final_blend,'Final Blend Model 05August2020')

Transformation Pipeline and Model Succesfully Saved

In [ ]: