Python pandas._libs.hashtable.Factorizer() Examples

The following are 3 code examples of pandas._libs.hashtable.Factorizer(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module pandas._libs.hashtable , or try the search function .
Example #1
Source File: merge.py    From vnpy_crypto with MIT License 4 votes vote down vote up
def _factorize_keys(lk, rk, sort=True):
    if is_datetime64tz_dtype(lk) and is_datetime64tz_dtype(rk):
        lk = lk.values
        rk = rk.values

    # if we exactly match in categories, allow us to factorize on codes
    if (is_categorical_dtype(lk) and
            is_categorical_dtype(rk) and
            lk.is_dtype_equal(rk)):
        klass = libhashtable.Int64Factorizer

        if lk.categories.equals(rk.categories):
            rk = rk.codes
        else:
            # Same categories in different orders -> recode
            rk = _recode_for_categories(rk.codes, rk.categories, lk.categories)

        lk = _ensure_int64(lk.codes)
        rk = _ensure_int64(rk)
    elif is_int_or_datetime_dtype(lk) and is_int_or_datetime_dtype(rk):
        klass = libhashtable.Int64Factorizer
        lk = _ensure_int64(com._values_from_object(lk))
        rk = _ensure_int64(com._values_from_object(rk))
    else:
        klass = libhashtable.Factorizer
        lk = _ensure_object(lk)
        rk = _ensure_object(rk)

    rizer = klass(max(len(lk), len(rk)))

    llab = rizer.factorize(lk)
    rlab = rizer.factorize(rk)

    count = rizer.get_count()

    if sort:
        uniques = rizer.uniques.to_array()
        llab, rlab = _sort_labels(uniques, llab, rlab)

    # NA group
    lmask = llab == -1
    lany = lmask.any()
    rmask = rlab == -1
    rany = rmask.any()

    if lany or rany:
        if lany:
            np.putmask(llab, lmask, count)
        if rany:
            np.putmask(rlab, rmask, count)
        count += 1

    return llab, rlab, count 
Example #2
Source File: merge.py    From Splunking-Crime with GNU Affero General Public License v3.0 4 votes vote down vote up
def _factorize_keys(lk, rk, sort=True):
    if is_datetime64tz_dtype(lk) and is_datetime64tz_dtype(rk):
        lk = lk.values
        rk = rk.values

    # if we exactly match in categories, allow us to factorize on codes
    if (is_categorical_dtype(lk) and
            is_categorical_dtype(rk) and
            lk.is_dtype_equal(rk)):
        klass = libhashtable.Int64Factorizer
        lk = _ensure_int64(lk.codes)
        rk = _ensure_int64(rk.codes)
    elif is_int_or_datetime_dtype(lk) and is_int_or_datetime_dtype(rk):
        klass = libhashtable.Int64Factorizer
        lk = _ensure_int64(com._values_from_object(lk))
        rk = _ensure_int64(com._values_from_object(rk))
    else:
        klass = libhashtable.Factorizer
        lk = _ensure_object(lk)
        rk = _ensure_object(rk)

    rizer = klass(max(len(lk), len(rk)))

    llab = rizer.factorize(lk)
    rlab = rizer.factorize(rk)

    count = rizer.get_count()

    if sort:
        uniques = rizer.uniques.to_array()
        llab, rlab = _sort_labels(uniques, llab, rlab)

    # NA group
    lmask = llab == -1
    lany = lmask.any()
    rmask = rlab == -1
    rany = rmask.any()

    if lany or rany:
        if lany:
            np.putmask(llab, lmask, count)
        if rany:
            np.putmask(rlab, rmask, count)
        count += 1

    return llab, rlab, count 
Example #3
Source File: merge.py    From elasticintel with GNU General Public License v3.0 4 votes vote down vote up
def _factorize_keys(lk, rk, sort=True):
    if is_datetime64tz_dtype(lk) and is_datetime64tz_dtype(rk):
        lk = lk.values
        rk = rk.values

    # if we exactly match in categories, allow us to factorize on codes
    if (is_categorical_dtype(lk) and
            is_categorical_dtype(rk) and
            lk.is_dtype_equal(rk)):
        klass = libhashtable.Int64Factorizer
        lk = _ensure_int64(lk.codes)
        rk = _ensure_int64(rk.codes)
    elif is_int_or_datetime_dtype(lk) and is_int_or_datetime_dtype(rk):
        klass = libhashtable.Int64Factorizer
        lk = _ensure_int64(com._values_from_object(lk))
        rk = _ensure_int64(com._values_from_object(rk))
    else:
        klass = libhashtable.Factorizer
        lk = _ensure_object(lk)
        rk = _ensure_object(rk)

    rizer = klass(max(len(lk), len(rk)))

    llab = rizer.factorize(lk)
    rlab = rizer.factorize(rk)

    count = rizer.get_count()

    if sort:
        uniques = rizer.uniques.to_array()
        llab, rlab = _sort_labels(uniques, llab, rlab)

    # NA group
    lmask = llab == -1
    lany = lmask.any()
    rmask = rlab == -1
    rany = rmask.any()

    if lany or rany:
        if lany:
            np.putmask(llab, lmask, count)
        if rany:
            np.putmask(rlab, rmask, count)
        count += 1

    return llab, rlab, count