I notice that this is an issue on GitHub already. Does anyone have any code that converts a Pandas DataFrame to an Orange Table?
Explicitly, I have the following table.
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
The documentation of Orange package didn't cover all the details. Table._init__(Domain, numpy.ndarray) works only for int and float according to lib_kernel.cpp.
They really should provide an C-level interface for pandas.DataFrames, or at least numpy.dtype("str") support.
Update: Adding table2df, df2table performance improved greatly by utilizing numpy for int and float.
Keep this piece of script in your orange python script collections, now you are equipped with pandas in your orange environment.
Usage: a_pandas_dataframe = table2df( a_orange_table ) , a_orange_table = df2table( a_pandas_dataframe )
Note: This script works only in Python 2.x, refer to @DustinTang 's answer for Python 3.x compatible script.
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)
In order to convert pandas DataFrame to Orange Table you need to construct a domain, which specifies the column types.
For continuous variables, you only need to provide the name of the variable, but for Discrete variables, you also need to provide a list of all possible values.
The following code will construct a domain for your DataFrame and convert it to an Orange Table:
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()])
The map(str, row) step is needed so Orange know that the data contains values of discrete features (and not the indices of values in the values list).
This code is revised from @TurtleIzzy for Python3.
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)
Something like this?
table = Orange.data.Table(df.as_matrix())
The columns in Orange will get generic names (a1, a2...). If you want to copy the names and the types from the data frame, construct Orange.data.Domain object (http://docs.orange.biolab.si/reference/rst/Orange.data.domain.html#Orange.data.Domain.init) from the data frame and pass it as the first argument above.
See the constructors in http://docs.orange.biolab.si/reference/rst/Orange.data.table.html.
Answer below from a closed issue on github
from Orange.data.pandas_compat import table_from_frame
out_data = table_from_frame(df)
Where df is your dataFrame. So far I've only noticed a need to manually define a domain to handle dates if the data source wasn't 100% clean and to the required ISO standard.
I realize this is an old question and a lot changed from when it was first asked - but this question comes up top on google search results on the topic.
来源：https://stackoverflow.com/questions/26320638/converting-pandas-dataframe-to-orange-table