comparison pre_process.xml @ 28:a12d5eae322e draft

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit 60f0fbc0eafd7c11bc60fb6c77f2937782efd8a9-dirty

27:f7e85579f2e6

            <![CDATA[
import sys
import json
import pandas
import pickle
from scipy.io import mmread
from scipy.io import mmwrite
from sklearn import preprocessing

sys.path.insert(0, '$__tool_directory__')
from utils import read_columns

input_json_path = sys.argv[1]
with open(input_json_path, "r") as param_handler:
    params = json.load(param_handler)

column_option = params["input_type"]["column_selector_options_1"]["selected_column_selector_option"]
if column_option in ["by_index_number", "all_but_by_index_number", "by_header_name", "all_but_by_header_name"]:
    c = params["input_type"]["column_selector_options_1"]["col1"]
else:
    c = None
X = read_columns(
        "$input_type.infile",
        c = c,
        c_option = column_option,
        sep='\t',
        header=header,
        parse_dates=True,
        encoding=None,
        index_col=None,
        tupleize_cols=False).astype(float)
#end if

preprocessor = params["input_type"]["pre_processors"]["selected_pre_processor"]
options = params["input_type"]["pre_processors"]["options"]

my_class = getattr(preprocessing, preprocessor)
estimator = my_class(**options)
estimator.fit(X)
result = estimator.transform(X)

#if $input_type.selected_input_type == "sparse":
with open("$outfile_transform", "wb") as transform_handler:
    mmwrite(transform_handler, result)
#else:
res = pandas.DataFrame(result)
res.to_csv(path_or_buf = "$outfile_transform", sep="\t", index=False, header=None)
#end if

#if $save:
with open("$outfile_fit", 'wb') as out_handler:
    pickle.dump(estimator, out_handler, pickle.HIGHEST_PROTOCOL)

            <param name="save" value="true"/>
            <output name="outfile_transform" file="prp_result05" ftype="tabular"/>
            <output name="outfile_fit" file="prp_model05" ftype="zip" compare="sim_size" delta="5"/>
        </test>
        <test>
            <param name="infile" value="csr_sparse2.mtx" ftype="txt"/>
            <param name="selected_input_type" value="sparse"/>
            <param name="selected_pre_processor" value="Imputer"/>
            <param name="save" value="true"/>
            <param name="axis" value="true"/>
            <output name="outfile_transform" file="prp_result06" ftype="tabular"/>
            <output name="outfile_fit" file="prp_model06" ftype="zip" compare="sim_size" delta="50"/>
        </test>
        <test>
            <param name="infile" value="train.tabular" ftype="tabular"/>
            <param name="selected_input_type" value="tabular"/>
            <param name="selected_column_selector_option" value="all_columns"/>
            <param name="selected_pre_processor" value="StandardScaler"/>
            <param name="save" value="true"/>

            <param name="selected_input_type" value="sparse"/>
            <param name="selected_pre_processor" value="Normalizer"/>
            <param name="save" value="true"/>
            <output name="outfile_transform" file="prp_result09" ftype="tabular"/>
            <output name="outfile_fit" file="prp_model09" ftype="zip" compare="sim_size" delta="5"/>
        </test>
    </tests>
    <help>
        <![CDATA[
**What it does**

28:a12d5eae322e

            <![CDATA[
import sys
import json
import pandas
import pickle

from scipy.io import mmread
from scipy.io import mmwrite
from sklearn import preprocessing
from galaxy_ml.utils import read_columns, SafeEval


safe_eval = SafeEval()

input_json_path = sys.argv[1]
with open(input_json_path, "r") as param_handler:
    params = json.load(param_handler)

column_option = params["input_type"]["column_selector_options_1"]["selected_column_selector_option"]
if column_option in ["by_index_number", "all_but_by_index_number", "by_header_name", "all_but_by_header_name"]:
    c = params["input_type"]["column_selector_options_1"]["col1"]
else:
    c = None
X, input_df = read_columns(
        "$input_type.infile",
        c=c,
        c_option=column_option,
        return_df=True,
        sep='\t',
        header=header,
        parse_dates=True,
        encoding=None,
        index_col=None,
        tupleize_cols=False)
X = X.astype(float)
#end if

preprocessor = params["input_type"]["pre_processors"]["selected_pre_processor"]
options = params["input_type"]["pre_processors"]["options"]
if 'feature_range' in options:
    feature_range = safe_eval(options['feature_range'].strip())
    if not feature_range:
        feature_range = (0, 1)
    options['feature_range'] = feature_range

my_class = getattr(preprocessing, preprocessor)
estimator = my_class(**options)
estimator.fit(X)
result = estimator.transform(X)

#if $input_type.selected_input_type == "sparse":
with open("$outfile_transform", "wb") as transform_handler:
    mmwrite(transform_handler, result)
#else:
columns = input_df.columns
if preprocessor == 'PolynomialFeatures':
    columns = None
    header = False
res = pandas.DataFrame(result, columns=columns)
res.to_csv(path_or_buf = "$outfile_transform", sep="\t",
           index=False, header=True if header else False)
#end if

#if $save:
with open("$outfile_fit", 'wb') as out_handler:
    pickle.dump(estimator, out_handler, pickle.HIGHEST_PROTOCOL)

            <param name="save" value="true"/>
            <output name="outfile_transform" file="prp_result05" ftype="tabular"/>
            <output name="outfile_fit" file="prp_model05" ftype="zip" compare="sim_size" delta="5"/>
        </test>
        <test>
            <param name="infile" value="train.tabular" ftype="tabular"/>
            <param name="selected_input_type" value="tabular"/>
            <param name="selected_column_selector_option" value="all_columns"/>
            <param name="selected_pre_processor" value="StandardScaler"/>
            <param name="save" value="true"/>

            <param name="selected_input_type" value="sparse"/>
            <param name="selected_pre_processor" value="Normalizer"/>
            <param name="save" value="true"/>
            <output name="outfile_transform" file="prp_result09" ftype="tabular"/>
            <output name="outfile_fit" file="prp_model09" ftype="zip" compare="sim_size" delta="5"/>
        </test>
        <test>
            <param name="infile" value="regression_X.tabular" ftype="tabular"/>
            <param name="header1" value="true"/>
            <param name="selected_column_selector_option" value="all_columns"/>
            <param name="selected_input_type" value="tabular"/>
            <param name="selected_pre_processor" value="MinMaxScaler"/>
            <param name="feature_range" value="(-1, 1)"/>
            <param name="save" value="false"/>
            <output name="outfile_transform" file="prp_result10" ftype="tabular"/>
        </test>
    </tests>
    <help>
        <![CDATA[
**What it does**