Note: A blank under the Pandas Equivalent Method means the method is equivalent to H2O. (Parenthesis are not always shown when need).
Last updated on 7/20/2017. If you notice an missing method, please submit a pull request with the addition or post a message to the h2ostream Google Group.
| H2OFrame Method | Pandas Equivalent Method |
|---|---|
| .abs | |
| .acos | .apply(lambda x: numpy.arccos(x), axis = 0) |
| .acosh | .apply(lambda x: numpy.arccosh(x), axis = 0) |
| .all | |
| .any | |
| .any_na_rm | |
| .anyfactor | |
| .apply | .apply |
| .as_data_frame | |
| .as_date | .to_datetime |
| .ascharacter | astype(str) |
| .asfactor | .astype('category') or .astype('object') |
| .asin | .apply(lambda x: numpy.arcsin(x), axis = 0) |
| .asinh | .apply(lambda x: numpy.arcsinh(x), axis = 0) |
| .asnumeric | astype(numpy.float) or apply(numpy.float) |
| .atan | .apply(lambda x: numpy.arctan(x), axis = 0) |
| .atanh | .apply(lambda x: numpy.arctanh(x), axis = 0) |
| .categories | .unique() |
| .cbind | .concat() |
| .ceil | .apply(numpy.ceil) |
| .col_names | .columns |
| .columns | |
| .columns_by_type | .select_dtypes() |
| .concat | |
| .cor | .corr |
| .cos | .apply(lambda x: numpy.arccoh(x), axis = 0) |
| .cosh | .apply(lambda x: numpy.arccos(x), axis = 0) |
| .cospi | .apply(lambda x: numpy.cos(numpy.pi * x), axis = 0) |
| .count | |
| .countmatches | .str.contains() |
| .cummax | |
| .cummin | |
| .cumprod | |
| .cumsum | |
| .cut | |
| .day | Series.dt.day |
| .dayOfWeek | DatetimeIndex(pandas_dataframe[time_column]).dayofweek |
| .ddply | |
| .describe | |
| .difflag1 | .diff |
| .digamma | scipy.special.digamma() |
| .dim | .shape |
| .drop | |
| .entropy | NA |
| .exp | numpy.exp() |
| .expm1 | numpy.expm1() |
| .filter_na_cols | NA |
| .flatten | |
| .floor | .apply(numpy.floor) |
| .frame | NA |
| .frame_id | NA |
| .from_python | NA |
| .gamma | scipy.special.gamma() |
| .get_frame | NA |
| .get_frame_data | similar to the purpose of to_csv() |
| .getrow | list(pandas_dataframe.loc[0,:]) |
| .group_by | .groupby() |
| .gsub | .replace() |
| .head | |
| .hist | |
| .hour | DatetimeIndex(pandas_dataframe[time_column]).year |
| .ifelse | numpy.where() |
| .impute | NA |
| .insert_missing_values | NA |
| .interaction | NA |
| .isax | NA |
| .ischaracter | .isinstance(pandas_column, object) |
| .isfactor | NA |
| .isin | |
| .isna | .isnull |
| .isnumeric | NA |
| .isstring | .isinstance(pandas_column, object) |
| .kfold_column | NA |
| .kurtosis | |
| .levels | .cat.categories, .unique() |
| .lgamma | scipy.special.gammaln() |
| .log | numpy.log() |
| .log10 | numpy.log10() |
| .log1p | numpy.log1p() |
| .log2 | numpy.log2() |
| .logical_negation | numpy.logical_not() |
| .lstrip | .str.lstrip('') |
| .match | |
| .max | |
| .mean | |
| .median | |
| .merge | |
| .min | |
| .mktime | |
| .mode | NA |
| .modulo_kfold_column | NA |
| .moment | pd.to_datetime() |
| .month | Series.dt.month |
| .mult | .dot |
| .na_omit | .dropna() |
| .nacnt | .isnull().sum() |
| .names | .columns |
| .nchar | .str.len() |
| .ncol | .shape[1] |
| .ncols | .shape[1] |
| .nlevels | .nunique() |
| .nrow | .shape[0] |
| .nrows | .shape[0] |
| .num_valid_substrings | |
| .pop | |
| .prod | |
| .quantile | |
| .rbind | |
| .refresh | |
| .relevel | NA |
| .rep_len | NA |
| .round | |
| .rstrip | .str.rstrip() |
| .runif | numpy.random.uniform() |
| .scale | sklearn.preprocessing.StandardScaler() |
| .sd | .std |
| .set_level | NA |
| .set_levels | NA |
| .set_name | .rename() |
| .set_names | .rename() |
| .shape | |
| .show | NA |
| .sign | numpy.sign() |
| .signif | NA |
| .sin | .apply(lambda x: numpy.sin(x), axis = 0) |
| .sinh | .apply(lambda x: numpy.sinh(x), axis = 0) |
| .sinpi | .apply(lambda x: numpy.sin(numpy.pi * x, axis = 0) |
| .skewness | .skew |
| .split_frame | NA |
| .sqrt | .apply(lambda x: numpy.sqrt(x), axis = 0) |
| .ss | NA |
| .stratified_kfold_column | sklearn.model_selection.StratifiedKFold |
| .stratified_split | sklearn.model_selection.StratifiedShuffleSplit |
| .strsplit | .str.split |
| .structure | NA |
| .sub | .str.replace() |
| .substring | .str.slice() |
| .sum | |
| .summary | .describe() |
| .table | .value_counts() |
| .tail | |
| .tan | .apply(lambda x: numpy.tan(x), axis = 0) |
| .tanh | .apply(lambda x: numpy.tanh(x), axis = 0) |
| .tanpi | .apply(lambda x: numpy.tan(numpy.pi * x, axis = 0) |
| .tolower | |
| .toupper | .apply(lambda x: x.upper(), inplace=True) |
| .transpose | |
| .trigamma | scipy.special.polygamma(x,3) |
| .trim | .str.strip |
| .trunc | |
| .type | .dtype |
| .types | .dtypes |
| .unique | |
| .var | |
| .week | Series.dt.week |
| .which | NA |
| .year | Series.dt.year |