将Pandas DataFrame转换为Orange Table

Question

我注意到这已经是GitHub上的一个问题了.有没有人有任何代码将Pandas DataFrame转换为Orange Table？

显然,我有下表.

       user  hotel  star_rating  user  home_continent  gender
0         1     39          4.0     1               2  female
1         1     44          3.0     1               2  female
2         2     63          4.5     2               3  female
3         2      2          2.0     2               3  female
4         3     26          4.0     3               1    male
5         3     37          5.0     3               1    male
6         3     63          4.5     3               1    male

Answer 1

Orange包的文档没有涵盖所有细节.Table._init__(Domain, numpy.ndarray)仅适用于int和float根据lib_kernel.cpp.

他们真的应该提供C级接口pandas.DataFrames,或至少numpy.dtype("str")支持.

更新:添加table2df,df2table通过利用numpy for int和float大大提高了性能.

将这段脚本保存在橙色python脚本集合中,现在你在橙色环境中配备了大熊猫.

用法:a_pandas_dataframe = table2df( a_orange_table ),a_orange_table = df2table( a_pandas_dataframe )

注意:此脚本仅适用于Python 2.x,请参阅@DustinTang 对Python 3.x兼容脚本的回答.

import pandas as pd
import numpy as np
import Orange

#### For those who are familiar with pandas
#### Correspondence:
####    value <-> Orange.data.Value
####        NaN <-> ["?", "~", "."] # Don't know, Don't care, Other
####    dtype <-> Orange.feature.Descriptor
####        category, int <-> Orange.feature.Discrete # category: > pandas 0.15
####        int, float <-> Orange.feature.Continuous # Continuous = core.FloatVariable
####                                                 # refer to feature/__init__.py
####        str <-> Orange.feature.String
####        object <-> Orange.feature.Python
####    DataFrame.dtypes <-> Orange.data.Domain
####    DataFrame.DataFrame <-> Orange.data.Table = Orange.orange.ExampleTable 
####                              # You will need this if you are reading sources

def series2descriptor(d, discrete=False):
    if d.dtype is np.dtype("float"):
        return Orange.feature.Continuous(str(d.name))
    elif d.dtype is np.dtype("int"):
        return Orange.feature.Continuous(str(d.name), number_of_decimals=0)
    else:
        t = d.unique()
        if discrete or len(t) < len(d) / 2:
            t.sort()
            return Orange.feature.Discrete(str(d.name), values=list(t.astype("str")))
        else:
            return Orange.feature.String(str(d.name))


def df2domain(df):
    featurelist = [series2descriptor(df.icol(col)) for col in xrange(len(df.columns))]
    return Orange.data.Domain(featurelist)


def df2table(df):
    # It seems they are using native python object/lists internally for Orange.data types (?)
    # And I didn't find a constructor suitable for pandas.DataFrame since it may carry
    # multiple dtypes
    #  --> the best approximate is Orange.data.Table.__init__(domain, numpy.ndarray),
    #  --> but the dtype of numpy array can only be "int" and "float"
    #  -->  * refer to src/orange/lib_kernel.cpp 3059:
    #  -->  *    if (((*vi)->varType != TValue::INTVAR) && ((*vi)->varType != TValue::FLOATVAR))
    #  --> Documents never mentioned >_<
    # So we use numpy constructor for those int/float columns, python list constructor for other

    tdomain = df2domain(df)
    ttables = [series2table(df.icol(i), tdomain[i]) for i in xrange(len(df.columns))]
    return Orange.data.Table(ttables)

    # For performance concerns, here are my results
    # dtndarray = np.random.rand(100000, 100)
    # dtlist = list(dtndarray)
    # tdomain = Orange.data.Domain([Orange.feature.Continuous("var" + str(i)) for i in xrange(100)])
    # tinsts = [Orange.data.Instance(tdomain, list(dtlist[i]) )for i in xrange(len(dtlist))] 
    # t = Orange.data.Table(tdomain, tinsts)
    #
    # timeit list(dtndarray)  # 45.6ms
    # timeit [Orange.data.Instance(tdomain, list(dtlist[i])) for i in xrange(len(dtlist))] # 3.28s
    # timeit Orange.data.Table(tdomain, tinsts) # 280ms

    # timeit Orange.data.Table(tdomain, dtndarray) # 380ms
    #
    # As illustrated above, utilizing constructor with ndarray can greatly improve performance
    # So one may conceive better converter based on these results


def series2table(series, variable):
    if series.dtype is np.dtype("int") or series.dtype is np.dtype("float"):
        # Use numpy
        # Table._init__(Domain, numpy.ndarray)
        return Orange.data.Table(Orange.data.Domain(variable), series.values[:, np.newaxis])
    else:
        # Build instance list
        # Table.__init__(Domain, list_of_instances)
        tdomain = Orange.data.Domain(variable)
        tinsts = [Orange.data.Instance(tdomain, [i]) for i in series]
        return Orange.data.Table(tdomain, tinsts)
        # 5x performance


def column2df(col):
    if type(col.domain[0]) is Orange.feature.Continuous:
        return (col.domain[0].name, pd.Series(col.to_numpy()[0].flatten()))
    else:
        tmp = pd.Series(np.array(list(col)).flatten())  # type(tmp) -> np.array( dtype=list (Orange.data.Value) )
        tmp = tmp.apply(lambda x: str(x[0]))
        return (col.domain[0].name, tmp)

def table2df(tab):
    # Orange.data.Table().to_numpy() cannot handle strings
    # So we must build the array column by column,
    # When it comes to strings, python list is used
    series = [column2df(tab.select(i)) for i in xrange(len(tab.domain))]
    series_name = [i[0] for i in series]  # To keep the order of variables unchanged
    series_data = dict(series)
    print series_data
    return pd.DataFrame(series_data, columns=series_name)

Answer 2

下面从github 上的一个已关闭问题中回答

from Orange.data.pandas_compat import table_from_frame
out_data = table_from_frame(df)

其中 df 是您的数据帧。到目前为止，我只注意到如果数据源不是 100% 干净且符合所需的 ISO 标准，则需要手动定义一个域来处理日期。

我意识到这是一个古老的问题，与第一次被问到时相比发生了很大变化 - 但这个问题在该主题的谷歌搜索结果中名列前茅。

Answer 3

from Orange.data.pandas_compat import table_from_frame,table_to_frame
df= table_to_frame(in_data)
#here you go
out_data = table_from_frame(df)

基于 Creo 的回答

Answer 4

为了将 pandas DataFrame 转换为 Orange Table，您需要构造一个域，它指定列类型。

对于连续变量，您只需要提供变量的名称，但对于离散变量，您还需要提供所有可能值的列表。

以下代码将为您的 DataFrame 构建一个域并将其转换为橙色表：

import numpy as np
from Orange.feature import Discrete, Continuous
from Orange.data import Domain, Table
domain = Domain([
    Discrete('user', values=[str(v) for v in np.unique(df.user)]),
    Discrete('hotel', values=[str(v) for v in np.unique(df.hotel)]),
    Continuous('star_rating'),
    Discrete('user', values=[str(v) for v in np.unique(df.user)]),
    Discrete('home_continent', values=[str(v) for v in np.unique(df.home_continent)]),
    Discrete('gender', values=['male', 'female'])], False)
table = Table(domain, [map(str, row) for row in df.as_matrix()])

需要 map(str, row) 步骤，以便 Orange 知道数据包含离散特征的值（而不是值列表中值的索引）。

Answer 5

此代码是根据 Python3 的 @TurtleIzzy 修订的。

import numpy as np
from Orange.data import Table, Domain, ContinuousVariable, DiscreteVariable


def series2descriptor(d):
    if d.dtype is np.dtype("float") or d.dtype is np.dtype("int"):
        return ContinuousVariable(str(d.name))
    else:
        t = d.unique()
        t.sort()
        return DiscreteVariable(str(d.name), list(t.astype("str")))

def df2domain(df):
    featurelist = [series2descriptor(df.iloc[:,col]) for col in range(len(df.columns))]
    return Domain(featurelist)

def df2table(df):
    tdomain = df2domain(df)
    ttables = [series2table(df.iloc[:,i], tdomain[i]) for i in range(len(df.columns))]
    ttables = np.array(ttables).reshape((len(df.columns),-1)).transpose()
    return Table(tdomain , ttables)

def series2table(series, variable):
    if series.dtype is np.dtype("int") or series.dtype is np.dtype("float"):
        series = series.values[:, np.newaxis]
        return Table(series)
    else:
        series = series.astype('category').cat.codes.reshape((-1,1))
        return Table(series)