Retentioneering: product analytics, data-driven customer journey map optimization, marketing analytics, web analytics, transaction analytics, graph visualization, and behavioral segmentation with customer segments in Python.

What is Retentioneering?

Retentioneering is a Python framework and library to assist product analysts and marketing analysts as it makes it easier to process and analyze clickstreams, event streams, trajectories, and event logs. You can segment users, clients (agents), build ML pipelines to predict agent category or probability of target event based on historical data.

In a common scenario you can use raw data from Google Analytics BigQuery stream or any other silimal streams in form of events and their timestamps for users, and Retentioneering is all you need to explore the user behavior from that data, it can reveal much more isights than funnel analytics, as it will automatically build the behavioral segments and their patterns, highlighting what events and pattern impact your conversion rates, retention and revenue.

Retentioneering extends Pandas, NetworkX, Scikit-learn for in-depth processing of event sequences data, specifically Retentioneering provides a powerful environment to perform an in-depth analysis of customer journey maps, bringing behavior-driven segmentation of users and machine learning pipelines to product analytics.

Most recent is Retentioneering 2.0.0, this version has major updates from 1.0.x and it is not reverse compatible with previous releases due to major syntax changes. With significant improvements we now provided architecture and the solid ground for farther updates and rapid development of analytical tools. Please update, leave your feedback and stay tuned.

Changelog

This is new major release Retentioneering 2.0. Change log is available here.

Complete documentation is available here.

Installation

Option 1. Run directly from google.colab. Open google.colab and click File-> “new notebook”. In the code cell run following to install Retentioneering (same command will install directly from Jupyter notebook):

!pip3 install retentioneering

Option 2. Install Retentioneering from PyPI:

pip3 install retentioneering

Option 3. Install Retentioneering directly from the source:

git clone https://github.com/retentioneering/retentioneering-tools
cd retentioneering-tools
python3 setup.py install

Quick start

Start using Retentioneering for clickstream analysis

Or directly open this notebook in Google Colab to run with sample data.

Suggested first steps:

import retentioneering

# load sample user behavior data as a pandas dataframe: 
data = retentioneering.datasets.load_simple_shop()

# update config to pass columns names:
retentioneering.config.update({
    'user_col': 'user_id',
    'event_col':'event',
    'event_time_col':'timestamp',
})

Above we imported sample dataset, which is regular pandas dataframe containing raw user behavior data from hypothetical web-site or app in form of sequence of records {'user_id', 'event', 'timestamp'}, and pass those column names to retentioneering.config. Now, let's plot the graph to visualize user behaviour from the dataset (read more about graphs here):

data.rete.plot_graph(norm_type='node',
                     weight_col='user_id',
                     thresh=0.2,
                     targets = {'payment_done':'green',
                                'lost':'red'})

Here we obtain the high-level graph of user activity where edge A --> B weight shows percent of users transitioning to event B from all users reached event A (note, edges with small weighs are thresholded to avoid visual clutter, read more in the documentation)

To automatically find distinct behavioral patterns we can cluster users from the dataset based on their behavior (read more about behavioral clustering here):

data.rete.get_clusters(method='kmeans',
                       n_clusters=8,
                       ngram_range=(1,2),
                       plot_type='cluster_bar',
                       targets=['payment_done','cart']);

Users with similar behavior grouped in the same cluster. Clusters with low conversion rate can represent systematic problem in the product: specific behavior pattern which does not lead to product goals. Obtained user segments can be explored deeper to understand problematic behavior pattern. In the example above for instance, cluster 4 has low conversion rate to purchase but high conversion rate to cart visit.

clus_4 = data.rete.filter_cluster(4)
clus_4.rete.plot_graph(thresh=0.1,
                        weight_col='user_id',
                        targets = {'lost':'red',
                                   'payment_done':'green'})

To explore more features please see the documentation

Step-by-step guides

Contributing

This is community-driven open source project in active development. Any contributions, new ideas, bug reports, bug fixes, documentation improvements are very welcome.

Retentioneering now provides several opensource solutions for data-driven product analytics and web analytics. Please checkout this repository for JS library to track the mutations of the website elements: https://github.com/retentioneering/retentioneering-dom-observer

Apps are better with math!:) Retentioneering is a research laboratory, analytics methodology and opensource tools founded by Maxim Godzi and Anatoly Zaytsev in 2015. Please feel free to contact us at [email protected] if you have any questions regarding this repo.

Got troubles with installation on macbook air m1.

python -V
Python 3.9.5

Part of the trace:

Building wheels for collected packages: numpy, llvmlite
  Building wheel for numpy (pyproject.toml) ... error
  error: subprocess-exited-with-error
  
  × Building wheel for numpy (pyproject.toml) did not run successfully.
  │ exit code: 1
  ╰─> [893 lines of output]
      Running from numpy source directory.
      numpy/random/_bounded_integers.pxd.in has not changed
      numpy/random/_philox.pyx has not changed
      numpy/random/_bounded_integers.pyx.in has not changed
      numpy/random/_sfc64.pyx has not changed
      numpy/random/_mt19937.pyx has not changed
      numpy/random/bit_generator.pyx has not changed
      Processing numpy/random/_bounded_integers.pyx
      numpy/random/mtrand.pyx has not changed
      numpy/random/_generator.pyx has not changed
      numpy/random/_pcg64.pyx has not changed
      numpy/random/_common.pyx has not changed
      Cythonizing sources
      blas_opt_info:
      blas_mkl_info:
      customize UnixCCompiler
        libraries mkl_rt not found in ['/Users/knodl/.pyenv/versions/3.9.5/envs/retentioneering/lib', '/usr/local/lib', '/usr/lib']
        NOT AVAILABLE
      
      blis_info:
        libraries blis not found in ['/Users/knodl/.pyenv/versions/3.9.5/envs/retentioneering/lib', '/usr/local/lib', '/usr/lib']
        NOT AVAILABLE
      
      openblas_info:
        libraries openblas not found in ['/Users/knodl/.pyenv/versions/3.9.5/envs/retentioneering/lib', '/usr/local/lib', '/usr/lib']
        NOT AVAILABLE
      
      atlas_3_10_blas_threads_info:
      Setting PTATLAS=ATLAS
        libraries tatlas not found in ['/Users/knodl/.pyenv/versions/3.9.5/envs/retentioneering/lib', '/usr/local/lib', '/usr/lib']
        NOT AVAILABLE
      
      atlas_3_10_blas_info:
        libraries satlas not found in ['/Users/knodl/.pyenv/versions/3.9.5/envs/retentioneering/lib', '/usr/local/lib', '/usr/lib']
        NOT AVAILABLE
      
      atlas_blas_threads_info:
      Setting PTATLAS=ATLAS
        libraries ptf77blas,ptcblas,atlas not found in ['/Users/knodl/.pyenv/versions/3.9.5/envs/retentioneering/lib', '/usr/local/lib', '/usr/lib']
        NOT AVAILABLE
      
      atlas_blas_info:
        libraries f77blas,cblas,atlas not found in ['/Users/knodl/.pyenv/versions/3.9.5/envs/retentioneering/lib', '/usr/local/lib', '/usr/lib']
        NOT AVAILABLE
      
      accelerate_info:
        libraries accelerate not found in ['/Users/knodl/.pyenv/versions/3.9.5/envs/retentioneering/lib', '/usr/local/lib', '/usr/lib']
      Library accelerate was not found. Ignoring
        libraries veclib not found in ['/Users/knodl/.pyenv/versions/3.9.5/envs/retentioneering/lib', '/usr/local/lib', '/usr/lib']
      Library veclib was not found. Ignoring
        FOUND:
          extra_compile_args = ['-faltivec', '-I/System/Library/Frameworks/vecLib.framework/Headers']
          extra_link_args = ['-Wl,-framework', '-Wl,Accelerate']
          define_macros = [('NO_ATLAS_INFO', 3), ('HAVE_CBLAS', None)]
      
        FOUND:
          extra_compile_args = ['-faltivec', '-I/System/Library/Frameworks/vecLib.framework/Headers']
          extra_link_args = ['-Wl,-framework', '-Wl,Accelerate']
          define_macros = [('NO_ATLAS_INFO', 3), ('HAVE_CBLAS', None)]
      
      non-existing path in 'numpy/distutils': 'site.cfg'
      lapack_opt_info:
      lapack_mkl_info:
        libraries mkl_rt not found in ['/Users/knodl/.pyenv/versions/3.9.5/envs/retentioneering/lib', '/usr/local/lib', '/usr/lib']
        NOT AVAILABLE
      
      openblas_lapack_info:
        libraries openblas not found in ['/Users/knodl/.pyenv/versions/3.9.5/envs/retentioneering/lib', '/usr/local/lib', '/usr/lib']
        NOT AVAILABLE
      
      openblas_clapack_info:
        libraries openblas,lapack not found in ['/Users/knodl/.pyenv/versions/3.9.5/envs/retentioneering/lib', '/usr/local/lib', '/usr/lib']
        NOT AVAILABLE
      
      flame_info:
        libraries flame not found in ['/Users/knodl/.pyenv/versions/3.9.5/envs/retentioneering/lib', '/usr/local/lib', '/usr/lib']
        NOT AVAILABLE
      
      atlas_3_10_threads_info:
      Setting PTATLAS=ATLAS
        libraries lapack_atlas not found in /Users/knodl/.pyenv/versions/3.9.5/envs/retentioneering/lib
        libraries tatlas,tatlas not found in /Users/knodl/.pyenv/versions/3.9.5/envs/retentioneering/lib
        libraries lapack_atlas not found in /usr/local/lib
        libraries tatlas,tatlas not found in /usr/local/lib
        libraries lapack_atlas not found in /usr/lib
        libraries tatlas,tatlas not found in /usr/lib
      <class 'numpy.distutils.system_info.atlas_3_10_threads_info'>
        NOT AVAILABLE
      
      atlas_3_10_info:
        libraries lapack_atlas not found in /Users/knodl/.pyenv/versions/3.9.5/envs/retentioneering/lib
        libraries satlas,satlas not found in /Users/knodl/.pyenv/versions/3.9.5/envs/retentioneering/lib
        libraries lapack_atlas not found in /usr/local/lib
        libraries satlas,satlas not found in /usr/local/lib
        libraries lapack_atlas not found in /usr/lib
        libraries satlas,satlas not found in /usr/lib
      <class 'numpy.distutils.system_info.atlas_3_10_info'>
        NOT AVAILABLE
      
      atlas_threads_info:
      Setting PTATLAS=ATLAS
        libraries lapack_atlas not found in /Users/knodl/.pyenv/versions/3.9.5/envs/retentioneering/lib
        libraries ptf77blas,ptcblas,atlas not found in /Users/knodl/.pyenv/versions/3.9.5/envs/retentioneering/lib
        libraries lapack_atlas not found in /usr/local/lib
        libraries ptf77blas,ptcblas,atlas not found in /usr/local/lib
        libraries lapack_atlas not found in /usr/lib
        libraries ptf77blas,ptcblas,atlas not found in /usr/lib
      <class 'numpy.distutils.system_info.atlas_threads_info'>
        NOT AVAILABLE
      
      atlas_info:
        libraries lapack_atlas not found in /Users/knodl/.pyenv/versions/3.9.5/envs/retentioneering/lib
        libraries f77blas,cblas,atlas not found in /Users/knodl/.pyenv/versions/3.9.5/envs/retentioneering/lib
        libraries lapack_atlas not found in /usr/local/lib
        libraries f77blas,cblas,atlas not found in /usr/local/lib
        libraries lapack_atlas not found in /usr/lib
        libraries f77blas,cblas,atlas not found in /usr/lib
      <class 'numpy.distutils.system_info.atlas_info'>
        NOT AVAILABLE
      
        FOUND:
          extra_compile_args = ['-faltivec', '-I/System/Library/Frameworks/vecLib.framework/Headers']
          extra_link_args = ['-Wl,-framework', '-Wl,Accelerate']
          define_macros = [('NO_ATLAS_INFO', 3), ('HAVE_CBLAS', None)]
      
      /private/var/folders/ws/ql7_7p_s7gbf_77z0hvwfw9w0000gn/T/pip-build-env-cxkr50mv/overlay/lib/python3.9/site-packages/setuptools/_distutils/dist.py:275: UserWarning: Unknown distribution option: 'define_macros'
        warnings.warn(msg)
      running bdist_wheel
      running build
      running config_cc
      unifing config_cc, config, build_clib, build_ext, build commands --compiler options
      running config_fc
      unifing config_fc, config, build_clib, build_ext, build commands --fcompiler options
      running build_src
      build_src
      building py_modules sources
      building library "npymath" sources
      Could not locate executable gfortran
      Could not locate executable f95
      Could not locate executable f90
      Could not locate executable f77
      Could not locate executable xlf90
      Could not locate executable xlf
      Could not locate executable ifort
      Could not locate executable ifc
      Could not locate executable g77
      Could not locate executable g95
      Could not locate executable pgfortran
      don't know how to compile Fortran code on platform 'posix'
        adding 'build/src.macosx-12.1-arm64-3.9/numpy/core/src/npymath' to include_dirs.
      None - nothing done with h_files = ['build/src.macosx-12.1-arm64-3.9/numpy/core/src/npymath/npy_math_internal.h']
      building library "npysort" sources
        adding 'build/src.macosx-12.1-arm64-3.9/numpy/core/src/common' to include_dirs.
      None - nothing done with h_files = ['build/src.macosx-12.1-arm64-3.9/numpy/core/src/common/npy_sort.h', 'build/src.macosx-12.1-arm64-3.9/numpy/core/src/common/npy_partition.h', 'build/src.macosx-12.1-arm64-3.9/numpy/core/src/common/npy_binsearch.h']
      building library "npyrandom" sources
      building extension "numpy.core._multiarray_tests" sources
      building extension "numpy.core._multiarray_umath" sources
        adding 'build/src.macosx-12.1-arm64-3.9/numpy/core/src/umath' to include_dirs.
        adding 'build/src.macosx-12.1-arm64-3.9/numpy/core/src/npymath' to include_dirs.
        adding 'build/src.macosx-12.1-arm64-3.9/numpy/core/src/common' to include_dirs.
      numpy.core - nothing done with h_files = ['build/src.macosx-12.1-arm64-3.9/numpy/core/src/umath/funcs.inc', 'build/src.macosx-12.1-arm64-3.9/numpy/core/src/umath/simd.inc', 'build/src.macosx-12.1-arm64-3.9/numpy/core/src/umath/loops.h', 'build/src.macosx-12.1-arm64-3.9/numpy/core/src/umath/matmul.h', 'build/src.macosx-12.1-arm64-3.9/numpy/core/src/umath/clip.h', 'build/src.macosx-12.1-arm64-3.9/numpy/core/src/npymath/npy_math_internal.h', 'build/src.macosx-12.1-arm64-3.9/numpy/core/src/common/templ_common.h', 'build/src.macosx-12.1-arm64-3.9/numpy/core/include/numpy/config.h', 'build/src.macosx-12.1-arm64-3.9/numpy/core/include/numpy/_numpyconfig.h', 'build/src.macosx-12.1-arm64-3.9/numpy/core/include/numpy/__multiarray_api.h', 'build/src.macosx-12.1-arm64-3.9/numpy/core/include/numpy/__ufunc_api.h']
      
     ...


      copying numpy/tests/test_scripts.py -> build/lib.macosx-12.1-arm64-3.9/numpy/tests
      running build_clib
      customize UnixCCompiler
      customize UnixCCompiler using new_build_clib
      building 'npymath' library
      compiling C sources
      C compiler: clang -Wno-unused-result -Wsign-compare -Wunreachable-code -DNDEBUG -g -fwrapv -O3 -Wall -I/Library/Developer/CommandLineTools/SDKs/MacOSX12.1.sdk/usr/include -I/Library/Developer/CommandLineTools/SDKs/MacOSX12.1.sdk/usr/include
      
      creating build/temp.macosx-12.1-arm64-3.9
      creating build/temp.macosx-12.1-arm64-3.9/numpy
      creating build/temp.macosx-12.1-arm64-3.9/numpy/core
      creating build/temp.macosx-12.1-arm64-3.9/numpy/core/src
      creating build/temp.macosx-12.1-arm64-3.9/numpy/core/src/npymath
      creating build/temp.macosx-12.1-arm64-3.9/build
      creating build/temp.macosx-12.1-arm64-3.9/build/src.macosx-12.1-arm64-3.9
      creating build/temp.macosx-12.1-arm64-3.9/build/src.macosx-12.1-arm64-3.9/numpy
      creating build/temp.macosx-12.1-arm64-3.9/build/src.macosx-12.1-arm64-3.9/numpy/core
      creating build/temp.macosx-12.1-arm64-3.9/build/src.macosx-12.1-arm64-3.9/numpy/core/src
      creating build/temp.macosx-12.1-arm64-3.9/build/src.macosx-12.1-arm64-3.9/numpy/core/src/npymath
      compile options: '-Ibuild/src.macosx-12.1-arm64-3.9/numpy/core/src/npymath -Inumpy/core/include -Ibuild/src.macosx-12.1-arm64-3.9/numpy/core/include/numpy -Inumpy/core/src/common -Inumpy/core/src -Inumpy/core -Inumpy/core/src/npymath -Inumpy/core/src/multiarray -Inumpy/core/src/umath -Inumpy/core/src/npysort -I/Users/knodl/.pyenv/versions/3.9.5/envs/retentioneering/include -I/Users/knodl/.pyenv/versions/3.9.5/include/python3.9 -Ibuild/src.macosx-12.1-arm64-3.9/numpy/core/src/common -Ibuild/src.macosx-12.1-arm64-3.9/numpy/core/src/npymath -c'
      clang: numpy/core/src/npymath/npy_math.c
      clang: numpy/core/src/npymath/halffloat.c
      clang: build/src.macosx-12.1-arm64-3.9/numpy/core/src/npymath/ieee754.c
      clang: build/src.macosx-12.1-arm64-3.9/numpy/core/src/npymath/npy_math_complex.c
      In file included from numpy/core/src/npymath/npy_math.c:9:
      numpy/core/src/npymath/npy_math_internal.h.src:490:21: warning: incompatible pointer types passing 'npy_longdouble *' (aka 'double *') to parameter of type 'long double *' [-Wincompatible-pointer-types]
          return modfl(x, iptr);
                          ^~~~
      /Library/Developer/CommandLineTools/SDKs/MacOSX12.1.sdk/usr/include/math.h:394:52: note: passing argument to parameter here
      extern long double modfl(long double, long double *);
                                                         ^
      1 warning generated.
      ar: adding 4 object files to build/temp.macosx-12.1-arm64-3.9/libnpymath.a
      ranlib:@ build/temp.macosx-12.1-arm64-3.9/libnpymath.a
      building 'npysort' library
      compiling C sources
      C compiler: clang -Wno-unused-result -Wsign-compare -Wunreachable-code -DNDEBUG -g -fwrapv -O3 -Wall -I/Library/Developer/CommandLineTools/SDKs/MacOSX12.1.sdk/usr/include -I/Library/Developer/CommandLineTools/SDKs/MacOSX12.1.sdk/usr/include
      
      creating build/temp.macosx-12.1-arm64-3.9/build/src.macosx-12.1-arm64-3.9/numpy/core/src/npysort
      compile options: '-Ibuild/src.macosx-12.1-arm64-3.9/numpy/core/src/common -Inumpy/core/include -Ibuild/src.macosx-12.1-arm64-3.9/numpy/core/include/numpy -Inumpy/core/src/common -Inumpy/core/src -Inumpy/core -Inumpy/core/src/npymath -Inumpy/core/src/multiarray -Inumpy/core/src/umath -Inumpy/core/src/npysort -I/Users/knodl/.pyenv/versions/3.9.5/envs/retentioneering/include -I/Users/knodl/.pyenv/versions/3.9.5/include/python3.9 -Ibuild/src.macosx-12.1-arm64-3.9/numpy/core/src/common -Ibuild/src.macosx-12.1-arm64-3.9/numpy/core/src/npymath -c'
      clang: build/src.macosx-12.1-arm64-3.9/numpy/core/src/npysort/quicksort.c
      clang: build/src.macosx-12.1-arm64-3.9/numpy/core/src/npysort/mergesort.c
      clang: build/src.macosx-12.1-arm64-3.9/numpy/core/src/npysort/timsort.c
      clang: build/src.macosx-12.1-arm64-3.9/numpy/core/src/npysort/heapsort.c
      clang: build/src.macosx-12.1-arm64-3.9/numpy/core/src/npysort/radixsort.c
      clang: build/src.macosx-12.1-arm64-3.9/numpy/core/src/npysort/selection.c
      clang: build/src.macosx-12.1-arm64-3.9/numpy/core/src/npysort/binsearch.c
      numpy/core/src/npysort/selection.c.src:328:9: warning: code will never be executed [-Wunreachable-code]
              npy_intp k;
              ^~~~~~~~~~~
      numpy/core/src/npysort/selection.c.src:326:14: note: silence by adding parentheses to mark code as explicitly dead
          else if (0 && kth == num - 1) {
                   ^
                   /* DISABLES CODE */ ( )
      numpy/core/src/npysort/selection.c.src:328:9: warning: code will never be executed [-Wunreachable-code]
              npy_intp k;
              ^~~~~~~~~~~
      numpy/core/src/npysort/selection.c.src:326:14: note: silence by adding parentheses to mark code as explicitly dead
          else if (0 && kth == num - 1) {
                   ^
                   /* DISABLES CODE */ ( )
      numpy/core/src/npysort/selection.c.src:328:9: warning: code will never be executed [-Wunreachable-code]
              npy_intp k;
              ^~~~~~~~~~~
      numpy/core/src/npysort/selection.c.src:326:14: note: silence by adding parentheses to mark code as explicitly dead
          else if (0 && kth == num - 1) {
                   ^
                   /* DISABLES CODE */ ( )
      numpy/core/src/npysort/selection.c.src:328:9: warning: code will never be executed [-Wunreachable-code]
              npy_intp k;
              ^~~~~~~~~~~
      numpy/core/src/npysort/selection.c.src:326:14: note: silence by adding parentheses to mark code as explicitly dead
          else if (0 && kth == num - 1) {
                   ^
                   /* DISABLES CODE */ ( )
      numpy/core/src/npysort/selection.c.src:328:9: warning: code will never be executed [-Wunreachable-code]
              npy_intp k;
              ^~~~~~~~~~~
      numpy/core/src/npysort/selection.c.src:326:14: note: silence by adding parentheses to mark code as explicitly dead
          else if (0 && kth == num - 1) {
                   ^
                   /* DISABLES CODE */ ( )
      numpy/core/src/npysort/selection.c.src:328:9: warning: code will never be executed [-Wunreachable-code]
              npy_intp k;
              ^~~~~~~~~~~
      numpy/core/src/npysort/selection.c.src:326:14: note: silence by adding parentheses to mark code as explicitly dead
          else if (0 && kth == num - 1) {
                   ^
                   /* DISABLES CODE */ ( )
      numpy/core/src/npysort/selection.c.src:328:9: warning: code will never be executed [-Wunreachable-code]
              npy_intp k;
              ^~~~~~~~~~~
      numpy/core/src/npysort/selection.c.src:326:14: note: silence by adding parentheses to mark code as explicitly dead
          else if (0 && kth == num - 1) {
                   ^
                   /* DISABLES CODE */ ( )
      numpy/core/src/npysort/selection.c.src:328:9: warning: code will never be executed [-Wunreachable-code]
              npy_intp k;
              ^~~~~~~~~~~
      numpy/core/src/npysort/selection.c.src:326:14: note: silence by adding parentheses to mark code as explicitly dead
          else if (0 && kth == num - 1) {
                   ^
                   /* DISABLES CODE */ ( )
      numpy/core/src/npysort/selection.c.src:328:9: warning: code will never be executed [-Wunreachable-code]
              npy_intp k;
              ^~~~~~~~~~~
      numpy/core/src/npysort/selection.c.src:326:14: note: silence by adding parentheses to mark code as explicitly dead
          else if (0 && kth == num - 1) {
                   ^
                   /* DISABLES CODE */ ( )
      numpy/core/src/npysort/selection.c.src:328:9: warning: code will never be executed [-Wunreachable-code]
              npy_intp k;
              ^~~~~~~~~~~
      numpy/core/src/npysort/selection.c.src:326:14: note: silence by adding parentheses to mark code as explicitly dead
          else if (0 && kth == num - 1) {
                   ^
                   /* DISABLES CODE */ ( )
      numpy/core/src/npysort/selection.c.src:328:9: warning: code will never be executed [-Wunreachable-code]
              npy_intp k;
              ^~~~~~~~~~~
      numpy/core/src/npysort/selection.c.src:326:14: note: silence by adding parentheses to mark code as explicitly dead
          else if (0 && kth == num - 1) {
                   ^
                   /* DISABLES CODE */ ( )
      numpy/core/src/npysort/selection.c.src:328:9: warning: code will never be executed [-Wunreachable-code]
              npy_intp k;
              ^~~~~~~~~~~
      numpy/core/src/npysort/selection.c.src:326:14: note: silence by adding parentheses to mark code as explicitly dead
          else if (0 && kth == num - 1) {
                   ^
                   /* DISABLES CODE */ ( )
      numpy/core/src/npysort/selection.c.src:328:9: warning: code will never be executed [-Wunreachable-code]
              npy_intp k;
              ^~~~~~~~~~~
      numpy/core/src/npysort/selection.c.src:326:14: note: silence by adding parentheses to mark code as explicitly dead
          else if (0 && kth == num - 1) {
                   ^
                   /* DISABLES CODE */ ( )
      numpy/core/src/npysort/selection.c.src:328:9: warning: code will never be executed [-Wunreachable-code]
              npy_intp k;
              ^~~~~~~~~~~
      numpy/core/src/npysort/selection.c.src:326:14: note: silence by adding parentheses to mark code as explicitly dead
          else if (0 && kth == num - 1) {
                   ^
                   /* DISABLES CODE */ ( )
      numpy/core/src/npysort/selection.c.src:328:9: warning: code will never be executed [-Wunreachable-code]
              npy_intp k;
              ^~~~~~~~~~~
      numpy/core/src/npysort/selection.c.src:326:14: note: silence by adding parentheses to mark code as explicitly dead
          else if (0 && kth == num - 1) {
                   ^
                   /* DISABLES CODE */ ( )
      numpy/core/src/npysort/selection.c.src:328:9: warning: code will never be executed [-Wunreachable-code]
              npy_intp k;
              ^~~~~~~~~~~
      numpy/core/src/npysort/selection.c.src:326:14: note: silence by adding parentheses to mark code as explicitly dead
          else if (0 && kth == num - 1) {
                   ^
                   /* DISABLES CODE */ ( )
      numpy/core/src/npysort/selection.c.src:328:9: warning: code will never be executed [-Wunreachable-code]
              npy_intp k;
              ^~~~~~~~~~~
      numpy/core/src/npysort/selection.c.src:326:14: note: silence by adding parentheses to mark code as explicitly dead
          else if (0 && kth == num - 1) {
                   ^
                   /* DISABLES CODE */ ( )
      numpy/core/src/npysort/selection.c.src:328:9: warning: code will never be executed [-Wunreachable-code]
              npy_intp k;
              ^~~~~~~~~~~
      numpy/core/src/npysort/selection.c.src:326:14: note: silence by adding parentheses to mark code as explicitly dead
          else if (0 && kth == num - 1) {
                   ^
                   /* DISABLES CODE */ ( )
      numpy/core/src/npysort/selection.c.src:328:9: warning: code will never be executed [-Wunreachable-code]
              npy_intp k;
              ^~~~~~~~~~~
      numpy/core/src/npysort/selection.c.src:326:14: note: silence by adding parentheses to mark code as explicitly dead
          else if (0 && kth == num - 1) {
                   ^
                   /* DISABLES CODE */ ( )
      numpy/core/src/npysort/selection.c.src:328:9: warning: code will never be executed [-Wunreachable-code]
              npy_intp k;
              ^~~~~~~~~~~
      numpy/core/src/npysort/selection.c.src:326:14: note: silence by adding parentheses to mark code as explicitly dead
          else if (0 && kth == num - 1) {
                   ^
                   /* DISABLES CODE */ ( )
      numpy/core/src/npysort/selection.c.src:328:9: warning: code will never be executed [-Wunreachable-code]
              npy_intp k;
              ^~~~~~~~~~~
      numpy/core/src/npysort/selection.c.src:326:14: note: silence by adding parentheses to mark code as explicitly dead
          else if (0 && kth == num - 1) {
                   ^
                   /* DISABLES CODE */ ( )
      numpy/core/src/npysort/selection.c.src:328:9: warning: code will never be executed [-Wunreachable-code]
              npy_intp k;
              ^~~~~~~~~~~
      numpy/core/src/npysort/selection.c.src:326:14: note: silence by adding parentheses to mark code as explicitly dead
          else if (0 && kth == num - 1) {
                   ^
                   /* DISABLES CODE */ ( )
      22 warnings generated.
      ar: adding 7 object files to build/temp.macosx-12.1-arm64-3.9/libnpysort.a
      ranlib:@ build/temp.macosx-12.1-arm64-3.9/libnpysort.a
      building 'npyrandom' library
      compiling C sources
      C compiler: clang -Wno-unused-result -Wsign-compare -Wunreachable-code -DNDEBUG -g -fwrapv -O3 -Wall -I/Library/Developer/CommandLineTools/SDKs/MacOSX12.1.sdk/usr/include -I/Library/Developer/CommandLineTools/SDKs/MacOSX12.1.sdk/usr/include
      
      creating build/temp.macosx-12.1-arm64-3.9/numpy/random
      creating build/temp.macosx-12.1-arm64-3.9/numpy/random/src
      creating build/temp.macosx-12.1-arm64-3.9/numpy/random/src/distributions
      compile options: '-Inumpy/core/include -Ibuild/src.macosx-12.1-arm64-3.9/numpy/core/include/numpy -Inumpy/core/src/common -Inumpy/core/src -Inumpy/core -Inumpy/core/src/npymath -Inumpy/core/src/multiarray -Inumpy/core/src/umath -Inumpy/core/src/npysort -I/Users/knodl/.pyenv/versions/3.9.5/envs/retentioneering/include -I/Users/knodl/.pyenv/versions/3.9.5/include/python3.9 -Ibuild/src.macosx-12.1-arm64-3.9/numpy/core/src/common -Ibuild/src.macosx-12.1-arm64-3.9/numpy/core/src/npymath -c'
      clang: numpy/random/src/distributions/logfactorial.c
      clang: numpy/random/src/distributions/distributions.c
      clang: numpy/random/src/distributions/random_mvhg_marginals.c
      clang: numpy/random/src/distributions/random_mvhg_count.c
      clang: numpy/random/src/distributions/random_hypergeometric.c
      ar: adding 5 object files to build/temp.macosx-12.1-arm64-3.9/libnpyrandom.a
      ranlib:@ build/temp.macosx-12.1-arm64-3.9/libnpyrandom.a
      running build_ext
      customize UnixCCompiler
      customize UnixCCompiler using new_build_ext
      building 'numpy.core._multiarray_tests' extension
      compiling C sources
      C compiler: clang -Wno-unused-result -Wsign-compare -Wunreachable-code -DNDEBUG -g -fwrapv -O3 -Wall -I/Library/Developer/CommandLineTools/SDKs/MacOSX12.1.sdk/usr/include -I/Library/Developer/CommandLineTools/SDKs/MacOSX12.1.sdk/usr/include
      
      creating build/temp.macosx-12.1-arm64-3.9/build/src.macosx-12.1-arm64-3.9/numpy/core/src/multiarray
      creating build/temp.macosx-12.1-arm64-3.9/numpy/core/src/common
      compile options: '-DNPY_INTERNAL_BUILD=1 -DHAVE_NPY_CONFIG_H=1 -D_FILE_OFFSET_BITS=64 -D_LARGEFILE_SOURCE=1 -D_LARGEFILE64_SOURCE=1 -Inumpy/core/include -Ibuild/src.macosx-12.1-arm64-3.9/numpy/core/include/numpy -Inumpy/core/src/common -Inumpy/core/src -Inumpy/core -Inumpy/core/src/npymath -Inumpy/core/src/multiarray -Inumpy/core/src/umath -Inumpy/core/src/npysort -I/Users/knodl/.pyenv/versions/3.9.5/envs/retentioneering/include -I/Users/knodl/.pyenv/versions/3.9.5/include/python3.9 -Ibuild/src.macosx-12.1-arm64-3.9/numpy/core/src/common -Ibuild/src.macosx-12.1-arm64-3.9/numpy/core/src/npymath -c'
      clang: build/src.macosx-12.1-arm64-3.9/numpy/core/src/multiarray/_multiarray_tests.c
      clang: numpy/core/src/common/mem_overlap.c
      In file included from numpy/core/src/multiarray/_multiarray_tests.c.src:7:
      In file included from numpy/core/include/numpy/npy_math.h:596:
      numpy/core/src/npymath/npy_math_internal.h.src:490:21: warning: incompatible pointer types passing 'npy_longdouble *' (aka 'double *') to parameter of type 'long double *' [-Wincompatible-pointer-types]
          return modfl(x, iptr);
                          ^~~~
      /Library/Developer/CommandLineTools/SDKs/MacOSX12.1.sdk/usr/include/math.h:394:52: note: passing argument to parameter here
      extern long double modfl(long double, long double *);
                                                         ^
      numpy/core/src/multiarray/_multiarray_tests.c.src:1895:61: warning: format specifies type 'long double' but the argument has type 'npy_longdouble' (aka 'double') [-Wformat]
              PyOS_snprintf(str, sizeof(str), "%.*Lg", precision, x);
                                               ~~~~~              ^
                                               %.*g
      2 warnings generated.
      clang -bundle -undefined dynamic_lookup -L/opt/homebrew/opt/readline/lib -L/opt/homebrew/opt/readline/lib -L/Users/knodl/.pyenv/versions/3.9.5/lib -L/opt/homebrew/lib -L/Library/Developer/CommandLineTools/SDKs/MacOSX12.1.sdk/usr/lib -L/opt/homebrew/opt/readline/lib -L/opt/homebrew/opt/readline/lib -L/Users/knodl/.pyenv/versions/3.9.5/lib -L/opt/homebrew/lib -L/Library/Developer/CommandLineTools/SDKs/MacOSX12.1.sdk/usr/lib build/temp.macosx-12.1-arm64-3.9/build/src.macosx-12.1-arm64-3.9/numpy/core/src/multiarray/_multiarray_tests.o build/temp.macosx-12.1-arm64-3.9/numpy/core/src/common/mem_overlap.o -Lbuild/temp.macosx-12.1-arm64-3.9 -lnpymath -o build/lib.macosx-12.1-arm64-3.9/numpy/core/_multiarray_tests.cpython-39-darwin.so
      building 'numpy.core._multiarray_umath' extension
      compiling C sources
      C compiler: clang -Wno-unused-result -Wsign-compare -Wunreachable-code -DNDEBUG -g -fwrapv -O3 -Wall -I/Library/Developer/CommandLineTools/SDKs/MacOSX12.1.sdk/usr/include -I/Library/Developer/CommandLineTools/SDKs/MacOSX12.1.sdk/usr/include
      
      creating build/temp.macosx-12.1-arm64-3.9/numpy/core/src/multiarray
      creating build/temp.macosx-12.1-arm64-3.9/numpy/core/src/umath
      creating build/temp.macosx-12.1-arm64-3.9/build/src.macosx-12.1-arm64-3.9/numpy/core/src/umath
      creating build/temp.macosx-12.1-arm64-3.9/build/src.macosx-12.1-arm64-3.9/numpy/core/src/common
      creating build/temp.macosx-12.1-arm64-3.9/private
      creating build/temp.macosx-12.1-arm64-3.9/private/var
      creating build/temp.macosx-12.1-arm64-3.9/private/var/folders
      creating build/temp.macosx-12.1-arm64-3.9/private/var/folders/ws
      creating build/temp.macosx-12.1-arm64-3.9/private/var/folders/ws/ql7_7p_s7gbf_77z0hvwfw9w0000gn
      creating build/temp.macosx-12.1-arm64-3.9/private/var/folders/ws/ql7_7p_s7gbf_77z0hvwfw9w0000gn/T
      creating build/temp.macosx-12.1-arm64-3.9/private/var/folders/ws/ql7_7p_s7gbf_77z0hvwfw9w0000gn/T/pip-install-4fdbvhnd
      creating build/temp.macosx-12.1-arm64-3.9/private/var/folders/ws/ql7_7p_s7gbf_77z0hvwfw9w0000gn/T/pip-install-4fdbvhnd/numpy_dafcb5869e1446f08f52deba357fec3d
      creating build/temp.macosx-12.1-arm64-3.9/private/var/folders/ws/ql7_7p_s7gbf_77z0hvwfw9w0000gn/T/pip-install-4fdbvhnd/numpy_dafcb5869e1446f08f52deba357fec3d/numpy
      creating build/temp.macosx-12.1-arm64-3.9/private/var/folders/ws/ql7_7p_s7gbf_77z0hvwfw9w0000gn/T/pip-install-4fdbvhnd/numpy_dafcb5869e1446f08f52deba357fec3d/numpy/_build_utils
      creating build/temp.macosx-12.1-arm64-3.9/private/var/folders/ws/ql7_7p_s7gbf_77z0hvwfw9w0000gn/T/pip-install-4fdbvhnd/numpy_dafcb5869e1446f08f52deba357fec3d/numpy/_build_utils/src
      compile options: '-DNPY_INTERNAL_BUILD=1 -DHAVE_NPY_CONFIG_H=1 -D_FILE_OFFSET_BITS=64 -D_LARGEFILE_SOURCE=1 -D_LARGEFILE64_SOURCE=1 -DNO_ATLAS_INFO=3 -DHAVE_CBLAS -Ibuild/src.macosx-12.1-arm64-3.9/numpy/core/src/umath -Ibuild/src.macosx-12.1-arm64-3.9/numpy/core/src/npymath -Ibuild/src.macosx-12.1-arm64-3.9/numpy/core/src/common -Inumpy/core/include -Ibuild/src.macosx-12.1-arm64-3.9/numpy/core/include/numpy -Inumpy/core/src/common -Inumpy/core/src -Inumpy/core -Inumpy/core/src/npymath -Inumpy/core/src/multiarray -Inumpy/core/src/umath -Inumpy/core/src/npysort -I/Users/knodl/.pyenv/versions/3.9.5/envs/retentioneering/include -I/Users/knodl/.pyenv/versions/3.9.5/include/python3.9 -Ibuild/src.macosx-12.1-arm64-3.9/numpy/core/src/common -Ibuild/src.macosx-12.1-arm64-3.9/numpy/core/src/npymath -c'
      extra options: '-faltivec -I/System/Library/Frameworks/vecLib.framework/Headers'
      clang: numpy/core/src/multiarray/alloc.c
      clang: numpy/core/src/multiarray/array_assign_scalar.c
      clang: numpy/core/src/multiarray/buffer.c
      clang: numpy/core/src/multiarray/datetime_strings.c
      clang: numpy/core/src/multiarray/conversion_utils.c
      clang: numpy/core/src/multiarray/common.c
      clang: build/src.macosx-12.1-arm64-3.9/numpy/core/src/multiarray/einsum.c
      clang: numpy/core/src/multiarray/descriptor.c
      clang: error: the clang compiler does not support 'faltivec', please use -maltivec and include altivec.h explicitly
      clang: error: the clang compiler does not support 'faltivec', please use -maltivec and include altivec.h explicitly
      clang: error: the clang compiler does not support 'faltivec', please use -maltivec and include altivec.h explicitly
      clang: numpy/core/src/multiarray/hashdescr.c
      clang: build/src.macosx-12.1-arm64-3.9/numpy/core/src/multiarray/lowlevel_strided_loops.c
      clang: numpy/core/src/multiarray/multiarraymodule.c
      clang: error: the clang compiler does not support 'faltivec', please use -maltivec and include altivec.h explicitly
      clang: error: the clang compiler does not support 'faltivec', please use -maltivec and include altivec.h explicitly
      clang: error: the clang compiler does not support 'faltivec', please use -maltivec and include altivec.h explicitly
      clang: numpy/core/src/multiarray/nditer_constr.c
      clang: error: the clang compiler does not support 'faltivec', please use -maltivec and include altivec.h explicitly
      clang: numpy/core/src/multiarray/refcount.c
      clang: error: the clang compiler does not support 'faltivec', please use -maltivec and include altivec.h explicitly
      clang: numpy/core/src/multiarray/temp_elide.c
      clang: numpy/core/src/multiarray/vdot.c
      clang: numpy/core/src/multiarray/scalarapi.c
      clang: error: the clang compiler does not support 'faltivec', please use -maltivec and include altivec.h explicitly
      clang: build/src.macosx-12.1-arm64-3.9/numpy/core/src/umath/loops.c
      clang: error: the clang compiler does not support 'faltivec', please use -maltivec and include altivec.h explicitly
      clang: error: the clang compiler does not support 'faltivec', please use -maltivec and include altivec.h explicitly
      clang: numpy/core/src/umath/ufunc_type_resolution.c
      clang: error: the clang compiler does not support 'faltivec', please use -maltivec and include altivec.h explicitly
      clang: numpy/core/src/umath/ufunc_object.c
      clang: error: the clang compiler does not support 'faltivec', please use -maltivec and include altivec.h explicitly
      clang: numpy/core/src/common/array_assign.c
      clang: error: the clang compiler does not support 'faltivec', please use -maltivec and include altivec.h explicitly
      clang: error: the clang compiler does not support 'faltivec', please use -maltivec and include altivec.h explicitly
      clang: build/src.macosx-12.1-arm64-3.9/numpy/core/src/npymath/ieee754.c
      clang: build/src.macosx-12.1-arm64-3.9/numpy/core/src/common/npy_cpu_features.c
      clang: numpy/core/src/common/ucsnarrow.c
      clang: error: the clang compiler does not support 'faltivec', please use -maltivec and include altivec.h explicitly
      clang: error: the clang compiler does not support 'faltivec', please use -maltivec and include altivec.h explicitly
      clang: /private/var/folders/ws/ql7_7p_s7gbf_77z0hvwfw9w0000gn/T/pip-install-4fdbvhnd/numpy_dafcb5869e1446f08f52deba357fec3d/numpy/_build_utils/src/apple_sgemv_fix.c
      clang: error: the clang compiler does not support 'faltivec', please use -maltivec and include altivec.h explicitly
      clang: error: the clang compiler does not support 'faltivec', please use -maltivec and include altivec.h explicitly
      clang: error: the clang compiler does not support 'faltivec', please use -maltivec and include altivec.h explicitly
      clang: error: the clang compiler does not support 'faltivec', please use -maltivec and include altivec.h explicitly
      clang: error: the clang compiler does not support 'faltivec', please use -maltivec and include altivec.h explicitly
      clang: error: the clang compiler does not support 'faltivec', please use -maltivec and include altivec.h explicitly
      clang: error: the clang compiler does not support 'faltivec', please use -maltivec and include altivec.h explicitly
      error: Command "clang -Wno-unused-result -Wsign-compare -Wunreachable-code -DNDEBUG -g -fwrapv -O3 -Wall -I/Library/Developer/CommandLineTools/SDKs/MacOSX12.1.sdk/usr/include -I/Library/Developer/CommandLineTools/SDKs/MacOSX12.1.sdk/usr/include -DNPY_INTERNAL_BUILD=1 -DHAVE_NPY_CONFIG_H=1 -D_FILE_OFFSET_BITS=64 -D_LARGEFILE_SOURCE=1 -D_LARGEFILE64_SOURCE=1 -DNO_ATLAS_INFO=3 -DHAVE_CBLAS -Ibuild/src.macosx-12.1-arm64-3.9/numpy/core/src/umath -Ibuild/src.macosx-12.1-arm64-3.9/numpy/core/src/npymath -Ibuild/src.macosx-12.1-arm64-3.9/numpy/core/src/common -Inumpy/core/include -Ibuild/src.macosx-12.1-arm64-3.9/numpy/core/include/numpy -Inumpy/core/src/common -Inumpy/core/src -Inumpy/core -Inumpy/core/src/npymath -Inumpy/core/src/multiarray -Inumpy/core/src/umath -Inumpy/core/src/npysort -I/Users/knodl/.pyenv/versions/3.9.5/envs/retentioneering/include -I/Users/knodl/.pyenv/versions/3.9.5/include/python3.9 -Ibuild/src.macosx-12.1-arm64-3.9/numpy/core/src/common -Ibuild/src.macosx-12.1-arm64-3.9/numpy/core/src/npymath -c numpy/core/src/multiarray/alloc.c -o build/temp.macosx-12.1-arm64-3.9/numpy/core/src/multiarray/alloc.o -MMD -MF build/temp.macosx-12.1-arm64-3.9/numpy/core/src/multiarray/alloc.o.d -faltivec -I/System/Library/Frameworks/vecLib.framework/Headers" failed with exit status 1
      [end of output]
  
  note: This error originates from a subprocess, and is likely not a problem with pip.
  ERROR: Failed building wheel for numpy

  Building wheel for llvmlite (setup.py) ... error
  error: subprocess-exited-with-error
  
  × python setup.py bdist_wheel did not run successfully.
  │ exit code: 1
  ╰─> [11 lines of output]
      running bdist_wheel
      /Users/knodl/.pyenv/versions/3.9.5/envs/retentioneering/bin/python3.9 /private/var/folders/ws/ql7_7p_s7gbf_77z0hvwfw9w0000gn/T/pip-install-4fdbvhnd/llvmlite_008ed1517dfb4868be790fe2deeb4363/ffi/build.py
      LLVM version... Traceback (most recent call last):
        File "/private/var/folders/ws/ql7_7p_s7gbf_77z0hvwfw9w0000gn/T/pip-install-4fdbvhnd/llvmlite_008ed1517dfb4868be790fe2deeb4363/ffi/build.py", line 220, in <module>
          main()
        File "/private/var/folders/ws/ql7_7p_s7gbf_77z0hvwfw9w0000gn/T/pip-install-4fdbvhnd/llvmlite_008ed1517dfb4868be790fe2deeb4363/ffi/build.py", line 214, in main
          main_posix('osx', '.dylib')
        File "/private/var/folders/ws/ql7_7p_s7gbf_77z0hvwfw9w0000gn/T/pip-install-4fdbvhnd/llvmlite_008ed1517dfb4868be790fe2deeb4363/ffi/build.py", line 134, in main_posix
          raise RuntimeError(msg) from None
      RuntimeError: Could not find a `llvm-config` binary. There are a number of reasons this could occur, please see: https://llvmlite.readthedocs.io/en/latest/admin-guide/install.html#using-pip for help.
      error: command '/Users/knodl/.pyenv/versions/3.9.5/envs/retentioneering/bin/python3.9' failed with exit code 1
      [end of output]
  
  note: This error originates from a subprocess, and is likely not a problem with pip.
  ERROR: Failed building wheel for llvmlite
  Running setup.py clean for llvmlite
Failed to build numpy llvmlite
ERROR: Could not build wheels for numpy, which is required to install pyproject.toml-based projects

ImportError: cannot import name 'img_as_float32'

Hi guys

I tried to get through your "first steps" guide but it raised an error on the start

from retentioneering import init_config
import pandas as pd

---------------------------------------------------------------------------
ImportError                               Traceback (most recent call last)
<ipython-input-21-fe4dd999c90a> in <module>()
----> 1 from retentioneering import init_config
      2 import pandas as pd

/anaconda3/lib/python3.6/site-packages/retentioneering/__init__.py in <module>()
----> 1 from retentioneering.core.utils import init_config
      2 from retentioneering.core.simulator import Simulator

/anaconda3/lib/python3.6/site-packages/retentioneering/core/utils.py in <module>()
     14 from retentioneering.visualization import plot
     15 from sklearn.linear_model import LogisticRegression
---> 16 from retentioneering.core.model import ModelDescriptor
     17 from retentioneering.core import node_metrics
     18 from retentioneering.core import preprocessing

/anaconda3/lib/python3.6/site-packages/retentioneering/core/model.py in <module>()
      5 
      6 
----> 7 import shap
      8 import eli5
      9 from eli5.sklearn import PermutationImportance

/anaconda3/lib/python3.6/site-packages/shap/__init__.py in <module>()
     10 from .explainers.linear import LinearExplainer
     11 from .explainers.partition import PartitionExplainer
---> 12 from .plots.summary import summary_plot
     13 from .plots.decision import decision_plot, multioutput_decision_plot
     14 from .plots.dependence import dependence_plot

/anaconda3/lib/python3.6/site-packages/shap/plots/summary.py in <module>()
     13     pass
     14 from . import labels
---> 15 from . import colors
     16 
     17 # TODO: remove unused title argument / use title argument

/anaconda3/lib/python3.6/site-packages/shap/plots/colors.py in <module>()
      5 
      6 import numpy as np
----> 7 import skimage.color
      8 
      9 try:

/anaconda3/lib/python3.6/site-packages/skimage/color/__init__.py in <module>()
----> 1 from .colorconv import (convert_colorspace,
      2                         guess_spatial_dimensions,
      3                         rgba2rgb,
      4                         rgb2hsv,
      5                         hsv2rgb,

/anaconda3/lib/python3.6/site-packages/skimage/color/colorconv.py in <module>()
     54 import numpy as np
     55 from scipy import linalg
---> 56 from ..util import dtype, dtype_limits
     57 
     58 

/anaconda3/lib/python3.6/site-packages/skimage/util/__init__.py in <module>()
----> 1 from .dtype import (img_as_float32, img_as_float64, img_as_float,
      2                     img_as_int, img_as_uint, img_as_ubyte,
      3                     img_as_bool, dtype_limits)
      4 from .shape import view_as_blocks, view_as_windows
      5 from .noise import random_noise

ImportError: cannot import name 'img_as_float32'

skimage version: 0.15.0

opened by mingghan 5

'ValueError: too many values to unpack (expected 2)' in early steps tutorial

I am getting this error on

data.retention.get_clusters(plot_type='cluster_heatmap')

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-47-ea4770463931> in <module>()
----> 1 data.retention.get_clusters(plot_type='cluster_heatmap')

/anaconda3/lib/python3.6/site-packages/retentioneering/core/utils.py in get_clusters(self, plot_type, refit_cluster, method, **kwargs)
    450         if not hasattr(self, 'clusters') or refit_cluster:
    451             clusterer = getattr(clustering, method)
--> 452             self.clusters, self._metrics = clusterer(features, **kwargs)
    453             self._create_cluster_mapping(features.index.values)
    454 

ValueError: too many values to unpack (expected 2)

Same on

data.retention.get_clusters(n_clusters=8, plot_type='cluster_tsne', refit_cluster=True);

opened by mingghan 4

Dev2
Update to 2.0.3 Minor technical pre-release before the major update in October 2021

New in this minor version:

updated lib dependencies

added support for another config init

Upcoming in 2.1 in October 2021:

Important: Deep redesign of graph editor, including interactive node list editing (excluding and merging nodes by deleting or grouping), live recalculation of raw clickstream from the graph view

New preprocessing tools

More tools to work with cohorts and segments

Sequence exploration tools: search for loops, cycles, n-grams, and their product metrics influence

New prediction pipeline

Important: new norms for graph, edgelists, and adjacency matrix based of group-averaged user transition probabilities

Tools for automated sampling by users and event filtering based on event importance

New clustering and vectorizing techniques specific for product science
opened by godzi 2
Error after installing via miniconda3
Created new enviroment using miniconda3

pip3 install retentioneering

Got an error while starting python3 kernel «ImportError: DLL load failed while importing win32api»

Fixed it by:

pip install pywin32 python path\to\python\Scripts\pywin32_postinstall.py -install
opened by ivan-toriya 2
Your starred Github rep for analytics is moved

Hi,

Python tools for user trajectories analysis Retentioneering are now moved. Previously started in App in the Air (https://github.com/appintheair/retentioneering-framework) it is now rebuilt, redeveloped and actively maintained by independent Retentioneering team at https://github.com/retentioneering/retentioneering-tools

Please join for best latest updates and new features, like better graph visualization in Python.

Watch, Star, Fork

Thanks, Retentioneering team

opened by danlenny 1

ModuleNotFoundError: No module named 'itermplot'

Hi,

importing retentioneering causes this error:

Python 3.8.12 (default, Mar 15 2022, 12:23:51)
[Clang 12.0.5 (clang-1205.0.22.11)] on darwin
Type "help", "copyright", "credits" or "license" for more information.
>>> import retentioneering
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/Users/katya/.pyenv/versions/rete/lib/python3.8/site-packages/retentioneering/__init__.py", line 30, in <module>
    from retentioneering.core.config import config, init_config
  File "/Users/katya/.pyenv/versions/rete/lib/python3.8/site-packages/retentioneering/core/config.py", line 9, in <module>
    from .core_functions.base_dataset import BaseDataset
  File "/Users/katya/.pyenv/versions/rete/lib/python3.8/site-packages/retentioneering/core/core_functions/__init__.py", line 10, in <module>
    from .step_matrix import step_matrix
  File "/Users/katya/.pyenv/versions/rete/lib/python3.8/site-packages/retentioneering/core/core_functions/step_matrix.py", line 9, in <module>
    from retentioneering.visualization import plot_step_matrix
  File "/Users/katya/.pyenv/versions/rete/lib/python3.8/site-packages/retentioneering/visualization/plot_step_matrix.py", line 10, in <module>
    import matplotlib.pyplot as plt
  File "/Users/katya/.pyenv/versions/rete/lib/python3.8/site-packages/matplotlib/pyplot.py", line 2230, in <module>
    switch_backend(rcParams["backend"])
  File "/Users/katya/.pyenv/versions/rete/lib/python3.8/site-packages/matplotlib/pyplot.py", line 267, in switch_backend
    class backend_mod(matplotlib.backend_bases._Backend):
  File "/Users/katya/.pyenv/versions/rete/lib/python3.8/site-packages/matplotlib/pyplot.py", line 268, in backend_mod
    locals().update(vars(importlib.import_module(backend_name)))
  File "/Users/katya/.pyenv/versions/3.8.12/lib/python3.8/importlib/__init__.py", line 127, in import_module
    return _bootstrap._gcd_import(name[level:], package, level)
ModuleNotFoundError: No module named 'itermplot'
>>>

opened by demidovakatya 0

Origin/loops&cycles

Added a new functional to the utils.py, fixed some minor bugs.

List of changes: Fixed _make_target Fixed insert_sleep_events Added matplotlib import

New functions: get_negative_users import matplotlib Is_cycle Is_loop get_fraction sequence_search Find_sequences Loop_search Find_loops Find_cycles

opened by SynthaxWarrior 0
ValueError on seaborn==0.11.2
Cell

data.rete.compare(groups=(test, control), function=conversion, test='mannwhitneyu', group_names=('test','control'))'

in tutorial doesn't work and fails with ValueError: cannot reindex on an axis with duplicate labels error. After downgrading to seaborn==0.11.1 error dissapear.
opened by SvetoforColumb 0
The telegram link on the official website is broken

Hey folks, Sorry if that is not the right place for raising such kinds of issues. I was trying to navigate the community in telegram but noticed the link https://t.me/retentioneering_meetups is no longer active. Can you navigate me to the right one, please?

opened by zkid18 0

ERROR: Could not build wheels for numpy

opened by knodl 0

AttributeError: 'RetentioneeringDataset' object has no attribute 'plot_graph'
The tutorial notebook (Google Colab) returns the error above when running the following code:

data.rete.plot_graph(norm_type=None, weight_col=None, thresh=250)
opened by StijnVanRijssel 6

2.0.1(Oct 8, 2020)

Completely reworked Retentioneering workflow: functions init_config() and retention.prepare() are removed. In 2.0 it is not required to initialize “positive” and “negative” events before the analysis. You can start exploring your user behavior data first and define targets when needed as optional parameters. To access all Retentioneering tools attribute “.retention” was renamed to “.rete”. To get started with an updated workflow refer to this guide.

plot_step_matrix() function was significantly reworked and renamed to step_matrix(). To read more about new step_matrix() functionality refer to this description

get_edgelist(), get_adjacency() and plot_graph() functions now have customizable weighting options (total nuber of events, normalized by full dataset, normalized by nodes, etc.). To learn more please fere to this description

new function compare() was added to compare two segments of users or test/control groups in AB test based on defined metrics. Read more about compare function in this description

Users' behavior segmentation was reworked and now works significantly faster and updated with new functionality. For more information refer to this description

Tools to plot user conversion funnels were reworked and improved. To learn more about new features read this description
Source code(tar.gz)
Source code(zip)

Retentioneering: product analytics, data-driven customer journey map optimization, marketing analytics, web analytics, transaction analytics, graph visualization, and behavioral segmentation with customer segments in Python.

Related tags

Overview

What is Retentioneering?

Changelog

Installation

Quick start

Step-by-step guides

Contributing

Comments

Releases(2.0.1)

2.0.1(Oct 8, 2020)

Owner

Retentioneering

Sensitivity Analysis Library in Python (Numpy). Contains Sobol, Morris, Fractional Factorial and FAST methods.

Program that predicts the NBA mvp based on data from previous years.

Cold Brew: Distilling Graph Node Representations with Incomplete or Missing Neighborhoods

Validated, scalable, community developed variant calling, RNA-seq and small RNA analysis

EOD Historical Data Python Library (Unofficial)

Basis Set Format Converter

Extract data from a wide range of Internet sources into a pandas DataFrame.

Churn prediction with PySpark

Bearsql allows you to query pandas dataframe with sql syntax.

PyNHD is a part of HyRiver software stack that is designed to aid in watershed analysis through web services.

Python Practicum - prepare for your Data Science interview or get a refresher.

collect training and calibration data for gaze tracking

This program analyzes a DNA sequence and outputs snippets of DNA that are likely to be protein-coding genes.

Lale is a Python library for semi-automated data science.

Open source platform for Data Science Management automation

Python Kalman filtering and optimal estimation library. Implements Kalman filter, particle filter, Extended Kalman filter, Unscented Kalman filter, g-h (alpha-beta), least squares, H Infinity, smoothers, and more. Has companion book 'Kalman and Bayesian Filters in Python'.

Pipeline and Dataset helpers for complex algorithm evaluation.

Office365 (Microsoft365) audit log analysis tool

CSV database for chihuahua (HUAHUA) blockchain transactions

An Indexer that works out-of-the-box when you have less than 100K stored Documents