I think it is a good idea to run automated unit tests at a commit time. Currently, this project uses travis, but I feel that it has a higher affinity for development using GitHub. In some cases, you may use two together as a trial. Please consider.

Example: https://github.com/stanfordmlgroup/ngboost

Along with that, I would like to automate tasks such as https://github.com/pycaret/pycaret/pull/336.

Note: I am using pycaret in a Databricks notebook to tackle a classification problem.

When doing a classification task using compare_models, I would see running results like this as the job progressed:

However, with the upgrade to 2.2.0, I no longer see the informative table, but this token from pandas:

This is a pandas styler object that is not rendering correctly in the notebook.

So, my question is, what do I need to do to render this table properly inline? Is there a pandas setting or pycaret parameter that needs to be set?

Snippet of current code:

from pycaret.classification import *

EXP = setup(data=data, 
            target='Tier', 
            ignore_features=['imdbId', 'DV', 'log(DV)'],
            train_size=0.8,
            silent=True)

top5Models = compare_models(exclude=excludeAlgs, 
                                sort='MCC',
                                fold=kFolds,
                                turbo=True,
                                verbose=True,
                                n_select=topN)

Thanks for all timely help

I am using a table with 1092 rows and 127 features plus one categorical target column and I am getting this error above. Any idea what could be going wrong here? The table contains integer values and the target column has a total of two classes.

 from pycaret.classification import * 
 clf1 = setup(data = data, 
         target = 'ORG',
         silent = False)
> MemoryError: Unable to allocate 116. GiB for an array with shape (15554265202,) and data type int64

I think, the data is not that big. Am I doing something wrong?

I was able to install Pycaret to CoLab but not Juptyer Notebooks via Anaconda. Pycaret will load and almost complete but each time regardless of how I install it (pip, conda) (terminal, Notebook) I get an error message
ERROR: Command errored out with exit status 1: command: /Applications/anaconda3/bin/python -c 'import sys, setuptools, tokenize; sys.argv[0] = '"'"'/private/var/folders/4c/zjb0c1753g70dgrrsb3xy6c80000gn/T/pip-install-qbhjy_h2/pycaret/setup.py'"'"'; file='"'"'/private/var/folders/4c/zjb0c1753g70dgrrsb3xy6c80000gn/T/pip-install-qbhjy_h2/pycaret/setup.py'"'"';f=getattr(tokenize, '"'"'open'"'"', open)(file);code=f.read().replace('"'"'\r\n'"'"', '"'"'\n'"'"');f.close();exec(compile(code, file, '"'"'exec'"'"'))' egg_info --egg-base pip-egg-info cwd: /private/var/folders/4c/zjb0c1753g70dgrrsb3xy6c80000gn/T/pip-install-qbhjy_h2/pycaret/ Complete output (8 lines): running egg_info creating pip-egg-info/pycaret.egg-info writing pip-egg-info/pycaret.egg-info/PKG-INFO writing dependency_links to pip-egg-info/pycaret.egg-info/dependency_links.txt writing requirements to pip-egg-info/pycaret.egg-info/requires.txt writing top-level names to pip-egg-info/pycaret.egg-info/top_level.txt writing manifest file 'pip-egg-info/pycaret.egg-info/SOURCES.txt' error: package directory 'pycaret' does not exist ERROR: Command errored out with exit status 1: python setup.py egg_info Check the logs for full command output

Please advice and thanks

predict_model inside classification module produces erroneous output when a unseen pandas dataframe is passed. Number of row in input and outputs are different.

issue #884

Changes

Added display_format

def plot_model(model, plot="2d", scale=1, display_format=None):
.
.
.
    if display_format=='streamlit'
        st.write(fig)
    else:
        fig.show()

Notes

• Didn't include import streamlit as st since this will only work inside streamlit anyway
• Didn't use st.plotly_chart since st.write can plot many types of charts and won't have to be changed if plotly is dropped later

Update

• Added display_format to anywhere plot_model can be called 😃
• Error handling

Additional:

In nlp.py where fig.iplot() is used, I had to change asFigure = save_param to asFigure = True because streamlit needs a plotly object to interpret (https://discuss.streamlit.io/t/cufflinks-in-streamlit/2232/2)

.
.
.
if display_format=='streamlit':
    fig = df.iplot(asFigure=True) # plotly obj needs to be returned for streamlit to interpret
    st.write(fig)
else:
    df.iplot()

Hi, I was wondering if we can have Bayesian Hyperparameter Optimization technique used instead of Random Grid. This will help with speed of tuning and allow us to scrape through much larger grid scientifically. We can have this enhancement along with ability to add custom grid in tuning.

Thanks

Add plot models for Spectral Density and FFT

plot_model(plot='spectrogram')
plot_model(plot='welch')
plot_model(plot='fft')

All three can be achieved through scipy functions. We just need to plot them using plotly.

I am unable to impute NaNs (missing values) with mean and constant using PyCaret. Their documentation says, it does that by default. However, I have tried both (manual and automatic) but nothing is working. I am using my own car sales dataset.

clf1 = setup(data = car_data, target = 'Price', numeric_imputation='mean', categorical_imputation='mode', train_size = 0.5)
clf1 = setup(data = car_data, target = 'Price', categorical_features = ['Make', 'Colour'])

predict_model() returns the label and score. Can we also return the prediction probabilities?

I did it personally by simply saving the sklearn pipe and model objects, and then running them using sklearn methods.

Description While trying to install Pycaret package, I am getting the below error : ERROR: Could not install packages due to an EnvironmentError: [WinError 5] Access is denied: 'C:\Users\SasanapY\AppData\Local\Continuum\anaconda3\Anaconda64bit\Library\bin\tbbmalloc.dll' Consider using the --user option or check the permissions.

Expected behavior: I expected to install pycaret package Actual behavior: Got the error : ERROR: Could not install packages due to an EnvironmentError: [WinError 5] Access is denied: 'C:\Users\SasanapY\AppData\Local\Continuum\anaconda3\Anaconda64bit\Library\bin\tbbmalloc.dll' Consider using the --user option or check the permissions.

Versions OS - Windows 10 Python Version - 3.7.4g the pycaret, I got the below

Describe the feature you want to add to this project

Hi Pycaret team @ngupta23, @moezali1 and @Yard1 please add evaluate_model for visualizing all the plots in time_series like train_test_split, ts, forecast,decomposition. etc. i have seen this feature for classification and regression. if this is added to time_series as well it's good to see all plots at one place.

Describe your proposed solution

...

Describe alternatives you've considered, if relevant

...

Additional context

...

Solution 3: Estimate the hyperparameters using only the train part of the first CV split

• This will require us to update self._get_y_data to include another split type. This will be taken up in a separate development.

Originally posted by @ngupta23 in https://github.com/pycaret/pycaret/issues/3202#issuecomment-1367589752

Describe the feature you want to add to this project

I am having difficulty understanding how to properly use sessions in my code. When I define a new setup, I am unable to specify the USI value. I have attempted to solve this issue by using the following code:

s = setup(data, target = 'quality', session_id=42, experiment_name = exp_name, log_experiment=True)
s.set_config('USI', version_name)

However, this creates a log before the USI is set, causing the USI values of the runs to not match the Session Initialized ... value. Additionally, when I run a new training and create a new setup, it is nested within the previous one.

I would like to be able to properly manage the session so that, for example, if I run compare_models() today and want to fine-tune a model from this session tomorrow, I can insert it into the same session.

Describe your proposed solution

I would like to see functions such as list_sessions(), get_session(), and also have better control over nested sessions. These functions and improved control would allow me to more effectively manage and manipulate sessions in my code.

Describe the changes you've made

1. Log data and model artifacts to DagsHub Storage.
2. Log experiments to an MLFlow remote hosted by DagsHub.

Type of change

Please delete options that are not relevant.

• [ ] Bug fix (non-breaking change which fixes an issue)
• [x] New feature (non-breaking change which adds functionality)
• [ ] Code style update (formatting, local variables)
• [ ] Breaking change (fix or feature that would cause existing functionality to not work as expected)
• [ ] This change requires a documentation update

Checklist:

• [x] My code follows the style guidelines of this project.
• [x] I have performed a self-review of my own code.
• [x] I have commented my code, particularly in hard-to-understand areas.
• [ ] I have made corresponding changes to the documentation.
• [ ] My changes generate no new warnings.
• [ ] I have added tests that prove my fix is effective or that my feature works.
• [ ] New and existing unit tests pass locally with my changes.
• [ ] Any dependent changes have been merged and published in downstream modules.

Signed-off-by: Antoni Baum [email protected]

Related Issue or bug

Info about Issue or bug

Closes https://github.com/pycaret/pycaret/issues/3178

Describe the changes you've made

Returns non-transformed dataframe instead of transformed one in predict_model, matching the behavior in Pycaret 2.0.

Type of change

Please delete options that are not relevant.

• [x] Bug fix (non-breaking change which fixes an issue)
• [ ] New feature (non-breaking change which adds functionality)
• [ ] Code style update (formatting, local variables)
• [ ] Breaking change (fix or feature that would cause existing functionality to not work as expected)
• [ ] This change requires a documentation update

How Has This Been Tested?

Please describe the tests that you ran to verify your changes. Provide instructions so we can reproduce.

Describe if there is any unusual behaviour of your code(Write NA if there isn't)

A clear and concise description of it.

Checklist:

• [ ] My code follows the style guidelines of this project.
• [ ] I have performed a self-review of my own code.
• [ ] I have commented my code, particularly in hard-to-understand areas.
• [ ] I have made corresponding changes to the documentation.
• [ ] My changes generate no new warnings.
• [ ] I have added tests that prove my fix is effective or that my feature works.
• [ ] New and existing unit tests pass locally with my changes.
• [ ] Any dependent changes have been merged and published in downstream modules.

Screenshots

Original | Updated :--------------------: |:--------------------: original screenshot | updated screenshot |

Related Issue or bug

Hi @AJarman

I discussed this with @moezali1 and @Yard1 in the meeting on 20220409 and this is the recommendation. We should add an argument to setup called forecast_limit: Optional[List[Union[int, float]] = None. By default, no limits are applied (same as today's functionality). If user wants to set limits, they can do it as follows:

forecast_limit = None # default - no limits
forecast_limit = [0, 10000000] # lower and upper limit
forecast_limit = [0, None]  # lower limit only
forecast_limit = [None, 10000000] # upper limit only

Coding Actions:

• Inside setup, there will have to be a check to make sure that if a list is passed, it has exactly 2 entries and the types are correct.

• If this is enabled, we should add a step to the transformation pipeline. The order of transformations will be as follows

  • Impute
  • Limit
  • Transform
  • Scale

Future enhancements and user customization

In the future, we will also extend the following arguments to accept Transformer objects directly so any user wanting to set custom arguments, can pass the object directly (this is similar to what the other modules such as regression and classification do in pycaret). This will do away with the need for the kwargs in setup.

transform_target = "box_cox"  # Today
transform_target = BoxCoxTransformer(limits = Sth, method="pearsonr")  # In the future (in lieu of transform_kwargs)

forecast_limit = [0, None] # current proposal
forecast_limit = ScaledLogitTransformer(0, None) # In the future (in lieu of transform_kwargs)

Let me know if this makes sense. Would be happy to discuss more if needed.

Thanks!

Closes #1766

Describe the changes you've made

I have implemented the sktime scaledLogitTransformer in the time series module. This is a pipeline step added after imputatation, before transformation and scaling. This currently only affects the target variable and is specified using a list of two values. Implementing the same for exogenous variables would also be straightforward, however at the moment I'm not sure how this would function in practice, given that they would presumably need different limits. I have left a 'stubbed' out option (elif) which would be used to implement passing an sktime estimator directly as specified in the future requirements, at present this raises a specific NotImplementedError, rather than the generic TypeError it would do for any other type.

Type of change

Please delete options that are not relevant.

• [x] New feature (non-breaking change which adds functionality)

How Has This Been Tested?

Unit tests have been added which use the airline dataset from conftest.py as a fixture. These test a combination of relevant inputs.

Describe if there is any unusual behaviour of your code(Write NA if there isn't)

NA

Checklist:

• [x] My code follows the style guidelines of this project.
• [x] I have performed a self-review of my own code.
• [x] I have commented my code, particularly in hard-to-understand areas.
• [x] I have made corresponding changes to the documentation.
• [x] My changes generate no new warnings.
• [x] I have added tests that prove my fix is effective or that my feature works.
• [] New and existing unit tests pass locally with my changes.
• [x] Any dependent changes have been merged and published in downstream modules.

Screenshots

Original | Updated :--------------------: |:--------------------: original screenshot | updated screenshot |