Python sklearn.manifold() Examples

def learn_tsne(data, **kwargs):
    """
    Calculates TSNE transformation for given matrix features.

    Parameters
    --------
    data: np.array
        Array of features.
    kwargs: optional
        Parameters for ``sklearn.manifold.TSNE()``

    Returns
    -------
    Calculated TSNE transform

    Return type
    -------
    np.ndarray
    """
    _tsne_filter = TSNE.get_params(TSNE)
    kwargs = {i: j for i, j in kwargs.items() if i in _tsne_filter}
    res = TSNE(random_state=0, **kwargs).fit_transform(data.values)
    return pd.DataFrame(res, index=data.index.values) 

def get_manifold(data, manifold_type, **kwargs):
    """
    Reduces number of dimensions.

    Parameters
    ---------
    data: pd.DataFrame
        Dataframe with features for clustering indexed as in ``retention_config.index_col``
    manifold_type: str
        Name dimensionality reduction method from ``sklearn.decomposition`` and ``sklearn.manifold``
    kwargs: optional
        Parameters for ``sklearn.decomposition`` and ``sklearn.manifold`` methods.

    Returns
    --------
    pd.DataFrame with reduced dimensions.

    Return type
    --------
    pd.DataFrame
    """
    if hasattr(decomposition, manifold_type):
        man = getattr(decomposition, manifold_type)
    elif hasattr(manifold, manifold_type):
        man = getattr(manifold, manifold_type)
    else:
        raise ValueError(f'There is not such manifold {manifold_type}')
    tsvd = man(**{i: j for i, j in kwargs.items() if i in man.get_params(man)})
    res = tsvd.fit_transform(data)
    return pd.DataFrame(res, index=data.index) 

def merge_features(features, metadata, meta_index_col=None, manifold_type=None, fillna=None, drop=False, **kwargs):
    """
    Adds metadata to TFIDF of trajectories. Eeduced if ``manifold_type`` is not ``None``.

    Parameters
    --------
    features: pd.DataFrame
        Dataframe with users` metadata.
    metadata: pd.DataFrame
        Dataframe with user or session properties or any other information you would like to extract as features (e.g. user properties, LTV values, etc.). Default: ``None``
    meta_index_col: str, optional
        Used when metadata is not ``None``. Name of column in ``metadata`` dataframe that contains the same ID as in ``index_col``, or if not defined, same as in retention_config (e.g ID of users or sessions). If ``None``, then index of metadata dataframe is used instead. Default: ``None``
    manifold_type: str, optional
        Name dimensionality reduction method from ``sklearn.decomposition`` and ``sklearn.manifold``. Default: ``None``
    fillna: optional
        Value for filling missing metadata for any ``index_col`` value. Default: ``None``
    drop: bool, optional
        If ``True``, then drops users which do not exist in ``metadata`` dataframe. Default: ``False``
    kwargs: optional
        Keyword arguments for ``sklearn.decomposition`` and ``sklearn.manifold`` methods.

    Returns
    -------
    Dataframe with trajectory features (possibly reduced) and users metadata.

    Return type
    -------
    pd.DataFrame
    """
    if manifold_type is not None:
        features = get_manifold(features, manifold_type, **kwargs)
    if meta_index_col is not None:
        metadata.index = metadata[meta_index_col].values
        metadata = metadata.drop(meta_index_col, 1)
    res = features.join(metadata, rsuffix='_meta',)
    if drop and (fillna is None):
        res = res[res.isnull().sum(1) == 0].copy()
    if fillna is not None:
        res = res.fillna(fillna)
    return res