SYMBOL INDEX (344 symbols across 27 files)

FILE: handyspark/extensions/common.py
  function call2 (line 3) | def call2(self, name, *a):

FILE: handyspark/extensions/evaluation.py
  function thresholds (line 8) | def thresholds(self):
  function roc (line 14) | def roc(self):
  function pr (line 25) | def pr(self):
  function fMeasureByThreshold (line 36) | def fMeasureByThreshold(self, beta=1.0):
  function precisionByThreshold (line 46) | def precisionByThreshold(self):
  function recallByThreshold (line 53) | def recallByThreshold(self):
  function getMetricsByThreshold (line 60) | def getMetricsByThreshold(self):
  function confusionMatrix (line 77) | def confusionMatrix(self, threshold=0.5):
  function print_confusion_matrix (line 97) | def print_confusion_matrix(self, threshold=0.5):
  function plot_roc_curve (line 118) | def plot_roc_curve(self, ax=None):
  function plot_pr_curve (line 128) | def plot_pr_curve(self, ax=None):
  function __init__ (line 138) | def __init__(self, scoreAndLabels, scoreCol='score', labelCol='label'):

FILE: handyspark/extensions/types.py
  function ret (line 4) | def ret(cls, expr):
  function ret (line 11) | def ret(self, expr):

FILE: handyspark/ml/base.py
  class HandyTransformers (line 7) | class HandyTransformers(object):
    method __init__ (line 16) | def __init__(self, df):
    method imputer (line 20) | def imputer(self):
    method fencer (line 27) | def fencer(self):
  class HasDict (line 35) | class HasDict(Params):
    method __init__ (line 42) | def __init__(self):
    method setDictValues (line 46) | def setDictValues(self, value):
    method getDictValues (line 54) | def getDictValues(self):
  class HandyImputer (line 62) | class HandyImputer(Transformer, HasDict, DefaultParamsReadable, DefaultP...
    method _transform (line 71) | def _transform(self, dataset):
    method statistics (line 105) | def statistics(self):
  class HandyFencer (line 109) | class HandyFencer(Transformer, HasDict, DefaultParamsReadable, DefaultPa...
    method _transform (line 118) | def _transform(self, dataset):
    method fences (line 155) | def fences(self):

FILE: handyspark/plot.py
  function title_fom_clause (line 15) | def title_fom_clause(clause):
  function consolidate_plots (line 18) | def consolidate_plots(fig, axs, title, clauses):
  function plot_correlations (line 44) | def plot_correlations(pdf, ax=None):
  function strat_scatterplot (line 50) | def strat_scatterplot(sdf, col1, col2, n=30):
  function scatterplot (line 64) | def scatterplot(sdf, col1, col2, n=30, ax=None):
  function strat_histogram (line 111) | def strat_histogram(sdf, colname, bins=10, categorical=False):
  function histogram (line 150) | def histogram(sdf, colname, bins=10, categorical=False, ax=None):
  function _gen_dict (line 186) | def _gen_dict(rc_name, properties):
  function draw_boxplot (line 196) | def draw_boxplot(ax, stats):
  function boxplot (line 223) | def boxplot(sdf, colnames, ax=None, showfliers=True, k=1.5, precision=.0...
  function post_boxplot (line 257) | def post_boxplot(axs, stats):
  function roc_curve (line 264) | def roc_curve(fpr, tpr, roc_auc, ax=None):
  function pr_curve (line 278) | def pr_curve(precision, recall, pr_auc, ax=None):

FILE: handyspark/sql/dataframe.py
  function toHandy (line 25) | def toHandy(self):
  function notHandy (line 30) | def notHandy(self):
  function agg (line 36) | def agg(f):
  function inccol (line 40) | def inccol(f):
  class Handy (line 44) | class Handy(object):
    method __init__ (line 45) | def __init__(self, df):
    method __deepcopy__ (line 69) | def __deepcopy__(self, memo):
    method __getitem__ (line 78) | def __getitem__(self, *args):
    method stages (line 113) | def stages(self):
    method statistics_ (line 119) | def statistics_(self):
    method fences_ (line 123) | def fences_(self):
    method is_classification (line 127) | def is_classification(self):
    method classes (line 131) | def classes(self):
    method nclasses (line 135) | def nclasses(self):
    method response (line 139) | def response(self):
    method ncols (line 143) | def ncols(self):
    method nrows (line 147) | def nrows(self):
    method shape (line 151) | def shape(self):
    method strata (line 155) | def strata(self):
    method strata_colnames (line 160) | def strata_colnames(self):
    method _stratify (line 166) | def _stratify(self, strata):
    method _clear_stratification (line 169) | def _clear_stratification(self):
    method _set_stratification (line 180) | def _set_stratification(self, strata, raw_combinations, raw_clauses, c...
    method _build_strat_plot (line 194) | def _build_strat_plot(self, n_rows, n_cols, **kwargs):
    method _update_types (line 202) | def _update_types(self):
    method _take_array (line 213) | def _take_array(self, colname, n):
    method _value_counts (line 225) | def _value_counts(self, colnames, dropna=True, raw=False):
    method _fillna (line 246) | def _fillna(self, target, values):
    method __stat_to_dict (line 267) | def __stat_to_dict(self, colname, stat):
    method _fill_values (line 276) | def _fill_values(self, continuous, categorical, strategy):
    method __fill_self (line 288) | def __fill_self(self, continuous, categorical, strategy):
    method _dense_to_array (line 310) | def _dense_to_array(self, colname, array_colname):
    method _agg (line 315) | def _agg(self, name, func, colnames):
    method _calc_fences (line 332) | def _calc_fences(self, colnames, k=1.5, precision=.01):
    method _calc_mahalanobis_distance (line 353) | def _calc_mahalanobis_distance(self, colnames, output_col='__mahalanob...
    method _set_mahalanobis_outliers (line 390) | def _set_mahalanobis_outliers(self, colnames, critical_value=.999,
    method _calc_bxp_stats (line 402) | def _calc_bxp_stats(self, fences_df, colname, showfliers=False):
    method set_response (line 475) | def set_response(self, colname):
    method disassemble (line 486) | def disassemble(self, colname, new_colnames=None):
    method to_metrics_RDD (line 491) | def to_metrics_RDD(self, prob_col, label):
    method corr (line 495) | def corr(self, colnames=None, method='pearson'):
    method fill (line 507) | def fill(self, *args, continuous=None, categorical=None, strategy=None):
    method isnull (line 514) | def isnull(self, ratio=False):
    method nunique (line 537) | def nunique(self, colnames=None):
    method outliers (line 544) | def outliers(self, colnames=None, ratio=False, method='tukey', **kwargs):
    method get_outliers (line 578) | def get_outliers(self, colnames=None, critical_value=.999):
    method remove_outliers (line 588) | def remove_outliers(self, colnames=None, critical_value=.999):
    method fence (line 598) | def fence(self, colnames, k=1.5):
    method value_counts (line 634) | def value_counts(self, colnames, dropna=True):
    method mode (line 638) | def mode(self, colname):
    method entropy (line 659) | def entropy(self, colnames):
    method mutual_info (line 688) | def mutual_info(self, colnames):
    method mean (line 737) | def mean(self, colnames):
    method min (line 741) | def min(self, colnames):
    method max (line 745) | def max(self, colnames):
    method percentile (line 749) | def percentile(self, colnames, perc=50, precision=.01):
    method median (line 759) | def median(self, colnames, precision=.01):
    method stddev (line 763) | def stddev(self, colnames):
    method var (line 767) | def var(self, colnames):
    method q1 (line 771) | def q1(self, colnames, precision=.01):
    method q3 (line 775) | def q3(self, colnames, precision=.01):
    method _strat_boxplot (line 779) | def _strat_boxplot(self, colnames, **kwargs):
    method boxplot (line 794) | def boxplot(self, colnames, ax=None, showfliers=True, k=1.5, precision...
    method _post_boxplot (line 801) | def _post_boxplot(self, res):
    method _strat_scatterplot (line 805) | def _strat_scatterplot(self, colnames, **kwargs):
    method scatterplot (line 810) | def scatterplot(self, colnames, ax=None, **kwargs):
    method _strat_hist (line 818) | def _strat_hist(self, colname, bins=10, **kwargs):
    method hist (line 830) | def hist(self, colname, bins=10, ax=None, **kwargs):
  class HandyGrouped (line 841) | class HandyGrouped(GroupedData):
    method __init__ (line 842) | def __init__(self, jgd, df, *args):
    method agg (line 848) | def agg(self, *exprs):
    method __repr__ (line 854) | def __repr__(self):
  class HandyFrame (line 858) | class HandyFrame(DataFrame):
    method __init__ (line 914) | def __init__(self, df, handy=None):
    method __getattribute__ (line 929) | def __getattribute__(self, name):
    method __repr__ (line 951) | def __repr__(self):
    method _get_strata (line 954) | def _get_strata(self):
    method _gen_row_ids (line 973) | def _gen_row_ids(self, *args):
    method _loc (line 981) | def _loc(self, lower_bound, upper_bound):
    method cols (line 988) | def cols(self):
    method pandas (line 1009) | def pandas(self):
    method transformers (line 1026) | def transformers(self):
    method stages (line 1036) | def stages(self):
    method response (line 1042) | def response(self):
    method is_classification (line 1048) | def is_classification(self):
    method classes (line 1054) | def classes(self):
    method nclasses (line 1060) | def nclasses(self):
    method ncols (line 1066) | def ncols(self):
    method nrows (line 1072) | def nrows(self):
    method shape (line 1078) | def shape(self):
    method statistics_ (line 1084) | def statistics_(self):
    method fences_ (line 1091) | def fences_(self):
    method values (line 1098) | def values(self):
    method notHandy (line 1107) | def notHandy(self):
    method set_safety_limit (line 1112) | def set_safety_limit(self, limit):
    method safety_off (line 1118) | def safety_off(self):
    method collect (line 1125) | def collect(self):
    method take (line 1144) | def take(self, num):
    method stratify (line 1152) | def stratify(self, strata):
    method transform (line 1163) | def transform(self, f, name=None, args=None, returnType=None):
    method apply (line 1168) | def apply(self, f, name=None, args=None, returnType=None):
    method assign (line 1173) | def assign(self, **kwargs):
    method isnull (line 1195) | def isnull(self, ratio=False):
    method nunique (line 1210) | def nunique(self):
    method outliers (line 1225) | def outliers(self, ratio=False, method='tukey', **kwargs):
    method get_outliers (line 1244) | def get_outliers(self, colnames=None, critical_value=.999):
    method remove_outliers (line 1260) | def remove_outliers(self, colnames=None, critical_value=.999):
    method set_response (line 1276) | def set_response(self, colname):
    method fill (line 1291) | def fill(self, *args, categorical=None, continuous=None, strategy=None):
    method fence (line 1319) | def fence(self, colnames, k=1.5):
    method disassemble (line 1343) | def disassemble(self, colname, new_colnames=None):
    method to_metrics_RDD (line 1364) | def to_metrics_RDD(self, prob_col='probability', label_col='label'):
  class Bucket (line 1385) | class Bucket(object):
    method __init__ (line 1401) | def __init__(self, colname, bins=5):
    method __repr__ (line 1407) | def __repr__(self):
    method colname (line 1411) | def colname(self):
    method _get_buckets (line 1414) | def _get_buckets(self, df):
    method _get_clauses (line 1425) | def _get_clauses(self, buckets):
  class Quantile (line 1436) | class Quantile(Bucket):
    method __repr__ (line 1452) | def __repr__(self):
    method _get_buckets (line 1455) | def _get_buckets(self, df):
  class HandyColumns (line 1465) | class HandyColumns(object):
    method __init__ (line 1481) | def __init__(self, df, handy, strata=None):
    method __getitem__ (line 1492) | def __getitem__(self, *args):
    method __repr__ (line 1554) | def __repr__(self):
    method numerical (line 1559) | def numerical(self):
    method categorical (line 1565) | def categorical(self):
    method continuous (line 1571) | def continuous(self):
    method string (line 1577) | def string(self):
    method array (line 1583) | def array(self):
    method mean (line 1588) | def mean(self):
    method min (line 1591) | def min(self):
    method max (line 1594) | def max(self):
    method median (line 1597) | def median(self, precision=.01):
    method stddev (line 1607) | def stddev(self):
    method var (line 1610) | def var(self):
    method percentile (line 1613) | def percentile(self, perc, precision=.01):
    method q1 (line 1625) | def q1(self, precision=.01):
    method q3 (line 1635) | def q3(self, precision=.01):
    method _value_counts (line 1645) | def _value_counts(self, dropna=True, raw=True):
    method value_counts (line 1649) | def value_counts(self, dropna=True):
    method entropy (line 1669) | def entropy(self):
    method mutual_info (line 1678) | def mutual_info(self):
    method mode (line 1688) | def mode(self):
    method corr (line 1702) | def corr(self, method='pearson'):
    method nunique (line 1718) | def nunique(self):
    method outliers (line 1732) | def outliers(self, ratio=False, method='tukey', **kwargs):
    method get_outliers (line 1751) | def get_outliers(self, critical_value=.999):
    method remove_outliers (line 1764) | def remove_outliers(self, critical_value=.999):
    method hist (line 1777) | def hist(self, bins=10, ax=None):
    method boxplot (line 1788) | def boxplot(self, ax=None, showfliers=True, k=1.5, precision=.01):
    method scatterplot (line 1802) | def scatterplot(self, ax=None):
  class HandyStrata (line 1812) | class HandyStrata(object):
    method __init__ (line 1820) | def __init__(self, handy, strata):
    method __repr__ (line 1873) | def __repr__(self):
    method __getattribute__ (line 1880) | def __getattribute__(self, name):

FILE: handyspark/sql/datetime.py
  class HandyDatetime (line 4) | class HandyDatetime(object):
    method __init__ (line 20) | def __init__(self, df, colname):
    method __getattribute__ (line 26) | def __getattribute__(self, name):

FILE: handyspark/sql/pandas.py
  class HandyPandas (line 7) | class HandyPandas(object):
    method __init__ (line 16) | def __init__(self, df):
    method __getitem__ (line 20) | def __getitem__(self, *args):
    method str (line 29) | def str(self):
    method dt (line 57) | def dt(self):
    method __getattribute__ (line 74) | def __getattribute__(self, name):

FILE: handyspark/sql/schema.py
  function generate_schema (line 25) | def generate_schema(columns, nullable_columns='all'):

FILE: handyspark/sql/string.py
  class HandyString (line 5) | class HandyString(object):
    method __init__ (line 18) | def __init__(self, df, colname):
    method _remove_accents (line 23) | def _remove_accents(input):
    method remove_accents (line 26) | def remove_accents(self):
    method __getattribute__ (line 31) | def __getattribute__(self, name):

FILE: handyspark/sql/transform.py
  class HandyTransform (line 21) | class HandyTransform(object):
    method _get_return (line 26) | def _get_return(sdf, f, args):
    method _signatureType (line 35) | def _signatureType(sig):
    method gen_pandas_udf (line 51) | def gen_pandas_udf(f, args=None, returnType=None):
    method gen_grouped_pandas_udf (line 75) | def gen_grouped_pandas_udf(sdf, f, args=None, returnType=None):
    method transform (line 97) | def transform(sdf, f, name=None, args=None, returnType=None):
    method apply (line 107) | def apply(sdf, f, name=None, args=None, returnType=None):
    method assign (line 117) | def assign(sdf, **kwargs):

FILE: handyspark/stats.py
  function StatisticalSummaryValues (line 6) | def StatisticalSummaryValues(sdf, colnames):
  function tTest (line 22) | def tTest(jvm, *ssvs):
  function KolmogorovSmirnovTest (line 36) | def KolmogorovSmirnovTest(sdf, colname, dist='normal', *params):

FILE: handyspark/util.py
  function none2default (line 10) | def none2default(value, default):
  function none2zero (line 13) | def none2zero(value):
  function ensure_list (line 16) | def ensure_list(value):
  function check_columns (line 24) | def check_columns(df, colnames):
  class bcolors (line 32) | class bcolors:
  class HandyException (line 42) | class HandyException(Exception):
    method __init__ (line 43) | def __init__(self, *args, **kwargs):
    method colortext (line 56) | def colortext(text, color_code):
    method errortext (line 60) | def errortext(text):
    method exception_summary (line 65) | def exception_summary():
  function get_buckets (line 94) | def get_buckets(rdd, buckets):
  function dense_to_array (line 140) | def dense_to_array(sdf, colname, new_colname):
  function disassemble (line 158) | def disassemble(sdf, colname, new_colnames=None):
  function get_jvm_class (line 192) | def get_jvm_class(cl):
  function call_scala_method (line 197) | def call_scala_method(py_class, scala_method, df, *args):
  function counts_to_df (line 233) | def counts_to_df(value_counts, colnames, n_points):

FILE: setup.py
  function readme (line 3) | def readme():

FILE: tests/handyspark/conftest.py
  function sdf (line 17) | def sdf():
  function sdates (line 21) | def sdates():
  function pdf (line 25) | def pdf():
  function pdates (line 30) | def pdates():
  function predicted (line 34) | def predicted():

FILE: tests/handyspark/extensions/test_evaluation.py
  function test_confusion_matrix (line 11) | def test_confusion_matrix(sdf):
  function test_get_metrics_by_threshold (line 30) | def test_get_metrics_by_threshold(sdf):

FILE: tests/handyspark/extensions/test_types.py
  function test_atomic_types (line 5) | def test_atomic_types():
  function test_composite_types (line 9) | def test_composite_types():

FILE: tests/handyspark/ml/test_base.py
  function test_imputer (line 7) | def test_imputer(sdf, pdf):
  function test_fencer (line 25) | def test_fencer(sdf, pdf):

FILE: tests/handyspark/sql/test_dataframe.py
  function test_to_from_handy (line 14) | def test_to_from_handy(sdf):
  function test_shape (line 20) | def test_shape(sdf):
  function test_response (line 23) | def test_response(sdf):
  function test_safety_limit (line 31) | def test_safety_limit(sdf):
  function test_safety_limit2 (line 49) | def test_safety_limit2(sdf):
  function test_values (line 64) | def test_values(sdf, pdf):
  function test_stages (line 70) | def test_stages(sdf):
  function test_value_counts (line 76) | def test_value_counts(sdf, pdf):
  function test_column_values (line 82) | def test_column_values(sdf, pdf):
  function test_dataframe_values (line 87) | def test_dataframe_values(sdf, pdf):
  function test_isnull (line 92) | def test_isnull(sdf, pdf):
  function test_nunique (line 101) | def test_nunique(sdf, pdf):
  function test_columns_nunique (line 108) | def test_columns_nunique(sdf, pdf):
  function test_outliers (line 114) | def test_outliers(sdf, pdf):
  function test_mean (line 129) | def test_mean(sdf, pdf):
  function test_stratified_mean (line 135) | def test_stratified_mean(sdf, pdf):
  function test_mode (line 141) | def test_mode(sdf, pdf):
  function test_median (line 154) | def test_median(sdf, pdf):
  function test_types (line 169) | def test_types(sdf):
  function test_fill_categorical (line 178) | def test_fill_categorical(sdf):
  function test_fill_continuous (line 184) | def test_fill_continuous(sdf, pdf):
  function test_sequential_fill (line 196) | def test_sequential_fill(sdf):
  function test_corr (line 204) | def test_corr(sdf, pdf):
  function test_stratified_corr (line 210) | def test_stratified_corr(sdf, pdf):
  function test_fence (line 216) | def test_fence(sdf, pdf):
  function test_stratified_fence (line 229) | def test_stratified_fence(sdf):
  function test_grouped_column_values (line 236) | def test_grouped_column_values(sdf, pdf):
  function test_bucket (line 242) | def test_bucket(sdf, pdf):
  function test_quantile (line 252) | def test_quantile(sdf, pdf):
  function test_stratify_length (line 262) | def test_stratify_length(sdf, pdf):
  function test_stratify_list (line 269) | def test_stratify_list(sdf, pdf):
  function test_stratify_pandas_df (line 277) | def test_stratify_pandas_df(sdf, pdf):
  function test_stratify_pandas_series (line 284) | def test_stratify_pandas_series(sdf, pdf):
  function test_stratify_spark_df (line 291) | def test_stratify_spark_df(sdf, pdf):
  function test_stratify_fill (line 298) | def test_stratify_fill(sdf, pdf):
  function test_repr (line 319) | def test_repr(sdf):
  function test_stratify_bucket (line 324) | def test_stratify_bucket(sdf):
  function test_stratified_nunique (line 334) | def test_stratified_nunique(sdf, pdf):
  function test_mahalanobis (line 340) | def test_mahalanobis(sdf, pdf):
  function test_entropy (line 350) | def test_entropy(sdf, pdf):
  function test_mutual_info (line 356) | def test_mutual_info(sdf, pdf):

FILE: tests/handyspark/sql/test_datetime.py
  function test_is_leap_year (line 4) | def test_is_leap_year(sdates, pdates):
  function test_strftime (line 11) | def test_strftime(sdates, pdates):
  function test_weekday_name (line 18) | def test_weekday_name(sdates, pdates):
  function test_round (line 25) | def test_round(sdates, pdates):

FILE: tests/handyspark/sql/test_pandas.py
  function test_between (line 5) | def test_between(sdf, pdf):
  function test_isin (line 12) | def test_isin(sdf, pdf):
  function test_isna (line 19) | def test_isna(sdf, pdf):
  function test_notna (line 26) | def test_notna(sdf, pdf):
  function test_clip (line 34) | def test_clip(sdf, pdf):
  function test_replace (line 41) | def test_replace(sdf, pdf):
  function test_round (line 48) | def test_round(sdf, pdf):

FILE: tests/handyspark/sql/test_schema.py
  function test_generate_schema (line 5) | def test_generate_schema(sdf):

FILE: tests/handyspark/sql/test_string.py
  function test_count (line 5) | def test_count(sdf, pdf):
  function test_find (line 12) | def test_find(sdf, pdf):
  function test_len (line 19) | def test_len(sdf, pdf):
  function test_rfind (line 26) | def test_rfind(sdf, pdf):
  function test_contains (line 34) | def test_contains(sdf, pdf):
  function test_startswith (line 41) | def test_startswith(sdf, pdf):
  function test_match (line 48) | def test_match(sdf, pdf):
  function test_isalpha (line 55) | def test_isalpha(sdf, pdf):
  function test_replace (line 63) | def test_replace(sdf, pdf):
  function test_repeat (line 70) | def test_repeat(sdf, pdf):
  function test_join (line 77) | def test_join(sdf, pdf):
  function test_pad (line 84) | def test_pad(sdf, pdf):
  function test_slice (line 91) | def test_slice(sdf, pdf):
  function test_slice_replace (line 98) | def test_slice_replace(sdf, pdf):
  function test_strip (line 105) | def test_strip(sdf, pdf):
  function test_wrap (line 112) | def test_wrap(sdf, pdf):
  function test_get (line 119) | def test_get(sdf, pdf):
  function test_center (line 126) | def test_center(sdf, pdf):
  function test_zfill (line 133) | def test_zfill(sdf, pdf):
  function test_normalize (line 140) | def test_normalize(sdf, pdf):
  function test_upper (line 147) | def test_upper(sdf, pdf):

FILE: tests/handyspark/sql/test_transform.py
  function test_apply_axis0 (line 5) | def test_apply_axis0(sdf, pdf):
  function test_apply_axis1 (line 15) | def test_apply_axis1(sdf, pdf):
  function test_transform_axis0 (line 28) | def test_transform_axis0(sdf, pdf):
  function test_transform_axis1 (line 38) | def test_transform_axis1(sdf, pdf):
  function test_assign_axis0 (line 51) | def test_assign_axis0(sdf, pdf):
  function test_assign_axis1 (line 58) | def test_assign_axis1(sdf, pdf):

FILE: tests/handyspark/test_plot.py
  function plot_to_base64 (line 10) | def plot_to_base64(fig):
  function plot_to_pixels (line 18) | def plot_to_pixels(fig, shape=None):
  function test_boxplot_single (line 30) | def test_boxplot_single(sdf, pdf):
  function test_boxplot_multiple (line 41) | def test_boxplot_multiple(sdf, pdf):
  function test_hist_categorical (line 57) | def test_hist_categorical(sdf, pdf):
  function test_hist_continuous (line 68) | def test_hist_continuous(sdf, pdf):
  function test_scatterplot (line 81) | def test_scatterplot(sdf, pdf):
  function test_stratified_boxplot (line 106) | def test_stratified_boxplot(sdf, pdf):
  function test_stratified_hist (line 123) | def test_stratified_hist(sdf, pdf):

FILE: tests/handyspark/test_stats.py
  function test_ks (line 5) | def test_ks(sdf):

FILE: tests/handyspark/test_util.py
  function test_dense_to_array (line 5) | def test_dense_to_array(sdf):
  function test_disassemble (line 12) | def test_disassemble(sdf):