trying to fix dataload issue

.ipynb_checkpoints/settings-checkpoint.ini

@@ -5,7 +5,7 @@
 ### Python library ###
 repo = dddex
 lib_name = %(repo)s
-version = 0.0.3
+version = 0.0.4
 min_python = 3.7
 license = apache2
 
@@ -30,13 +30,13 @@ audience = Developers
 author = kaiguender
 author_email = kai.guender@yahoo.de
 copyright = 2022 onwards, %(author)s
-description = To be added.
+description = The package "data-driven density estimation x" (dddex) turns any standard point forecasting model into an estimator of the underlying conditional density 
 keywords = nbdev jupyter notebook python
 language = English
 status = 3
 user = kaiguender
 
 ### Optional ###
-requirements = fastcore>=1.5.27 pandas>=1.3.0 sklearn tsfresh>=0.19.0 lightgbm>=3.3.2 tabulate>=0.8.10 ipdb 
+requirements = fastcore>=1.5.27 pandas>=1.3.0 sklearn tsfresh>=0.19.0 lightgbm>=3.3.2 tabulate>=0.8.10
 # dev_requirements = 
 # console_scripts =

.ipynb_checkpoints/setup-checkpoint.py

@@ -0,0 +1,58 @@
+from pkg_resources import parse_version
+from configparser import ConfigParser
+import setuptools
+assert parse_version(setuptools.__version__)>=parse_version('36.2')
+
+# note: all settings are in settings.ini; edit there, not here
+config = ConfigParser(delimiters=['='])
+config.read('settings.ini')
+cfg = config['DEFAULT']
+
+cfg_keys = 'version description keywords author author_email'.split()
+expected = cfg_keys + "lib_name user branch license status min_python audience language".split()
+for o in expected: assert o in cfg, "missing expected setting: {}".format(o)
+setup_cfg = {o:cfg[o] for o in cfg_keys}
+
+licenses = {
+    'apache2': ('Apache Software License 2.0','OSI Approved :: Apache Software License'),
+    'mit': ('MIT License', 'OSI Approved :: MIT License'),
+    'gpl2': ('GNU General Public License v2', 'OSI Approved :: GNU General Public License v2 (GPLv2)'),
+    'gpl3': ('GNU General Public License v3', 'OSI Approved :: GNU General Public License v3 (GPLv3)'),
+    'bsd3': ('BSD License', 'OSI Approved :: BSD License'),
+}
+statuses = [ '1 - Planning', '2 - Pre-Alpha', '3 - Alpha',
+    '4 - Beta', '5 - Production/Stable', '6 - Mature', '7 - Inactive' ]
+py_versions = '3.6 3.7 3.8 3.9 3.10'.split()
+
+requirements = cfg.get('requirements','').split()
+if cfg.get('pip_requirements'): requirements += cfg.get('pip_requirements','').split()
+min_python = cfg['min_python']
+lic = licenses.get(cfg['license'].lower(), (cfg['license'], None))
+dev_requirements = (cfg.get('dev_requirements') or '').split()
+
+setuptools.setup(
+    name = cfg['lib_name'],
+    license = lic[0],
+    classifiers = [
+        'Development Status :: ' + statuses[int(cfg['status'])],
+        'Intended Audience :: ' + cfg['audience'].title(),
+        'Natural Language :: ' + cfg['language'].title(),
+    ] + ['Programming Language :: Python :: '+o for o in py_versions[py_versions.index(min_python):]] + (['License :: ' + lic[1] ] if lic[1] else []),
+    url = cfg['git_url'],
+    packages = setuptools.find_packages(),
+    include_package_data = True,
+    package_data={'': ['datasets/*.csv']},
+    install_requires = requirements,
+    extras_require={ 'dev': dev_requirements },
+    dependency_links = cfg.get('dep_links','').split(),
+    python_requires  = '>=' + cfg['min_python'],
+    long_description = open('README.md').read(),
+    long_description_content_type = 'text/markdown',
+    zip_safe = False,
+    entry_points = {
+        'console_scripts': cfg.get('console_scripts','').split(),
+        'nbdev': [f'{cfg.get("lib_path")}={cfg.get("lib_path")}._modidx:d']
+    },
+    **setup_cfg)
+
+

README.md

@@ -68,6 +68,90 @@ dataYaz, XTrain, yTrain, XTest, yTest = loadDataYaz(testDays = 28, returnXY = Tr
 LGBM = LGBMRegressor(n_jobs = 1)
 ```
 
+``` python
+loadDataYaz??
+```
+
+    Signature: loadDataYaz(testDays=28, returnXY=True, daysToCut=0)
+    Docstring: <no docstring>
+    Source:   
+    def loadDataYaz(testDays = 28, returnXY = True, daysToCut = 0):
+        
+        currentFile = __file__
+        scriptPath = os.path.realpath(currentFile)  # /home/user/test/my_script.py
+        dirPath = os.path.dirname(scriptPath)  # /home/user/test
+        
+        dataDirPath = join(dirPath, 'datasets')
+        dataPath = join(dataDirPath, 'dataYaz.csv')
+        
+        data = pd.read_csv(dataPath)
+        
+        # Cutting away daysToCut-many at end of data: Useful for evaluating
+        # evaluation on data in a rolled manner
+        cutOffDate = data.dayIndex.max() - daysToCut
+        data = data[data['dayIndex'] <= cutOffDate].reset_index(drop = True)
+        
+        # Label
+        if isinstance(testDays, int):
+            nDaysTest = testDays
+        else:
+            tsSizes = data.groupby(['id']).size()
+            nDaysTest = int(tsSizes.iloc[0] * testDays)
+            
+        cutoffDateTest = data.dayIndex.max() - nDaysTest
+        data['label'] = ['train' if data.dayIndex.iloc[i] <= cutoffDateTest else 'test' for i in range(data.shape[0])]    
+
+        # Normalize Demand
+        scalingData = data[data.label == 'train'].groupby('id')['demand'].agg('max').reset_index()
+        scalingData.rename(columns = {'demand': 'scalingValue'}, inplace = True)
+        data = pd.merge(data, scalingData, on = 'id')
+
+        data['demand'] = data.demand / data.scalingValue
+
+        #---
+
+        # Add lag features
+        y = pd.DataFrame(data['demand'])
+        X = data.drop(columns = ['demand'])
+
+        # set lag features
+        fc_parameters = MinimalFCParameters()
+
+        # delete length features
+        del fc_parameters['length']
+
+        # create lag features
+        X, y = add_lag_features(X = X, 
+                                y = y, 
+                                column_id = ['id'], 
+                                column_sort = 'dayIndex', 
+                                feature_dict = fc_parameters, 
+                                time_windows = [(7, 7), (14, 14), (28, 28)])
+        
+        data = pd.concat([y, X], axis = 1)
+                          
+        # Turn y from Series or dataframe to flatted array
+        y = np.ravel(y)
+        
+        #---
+        
+        X = np.array(data.drop(['demand', 'label', 'id'], axis = 1))
+        
+        XTrain = X[data['label'] == 'train']
+        yTrain = y[data['label'] == 'train']
+        
+        XTest = X[data['label'] == 'test']
+        yTest = y[data['label'] == 'test']
+        
+        #---
+        
+        if returnXY:
+            return data, XTrain, yTrain, XTest, yTest
+        else:
+            return data
+    File:      ~/dddex/dddex/loadData.py
+    Type:      function
+
 There are three parameters for
 [`LevelSetKDEx`](https://kaiguender.github.io/dddex/levelsetkdex.html#levelsetkdex):
 

_proc/04_loadData.ipynb

@@ -49,7 +49,7 @@
       "text/markdown": [
        "---\n",
        "\n",
-       "[source](https://github.com/kaiguender/dddex/blob/main/dddex/loadData.py#L22){target=\"_blank\" style=\"float:right; font-size:smaller\"}\n",
+       "[source](https://github.com/kaiguender/dddex/blob/main/dddex/loadData.py#L24){target=\"_blank\" style=\"float:right; font-size:smaller\"}\n",
        "\n",
        "### loadDataYaz\n",
        "\n",
@@ -58,7 +58,7 @@
       "text/plain": [
        "---\n",
        "\n",
-       "[source](https://github.com/kaiguender/dddex/blob/main/dddex/loadData.py#L22){target=\"_blank\" style=\"float:right; font-size:smaller\"}\n",
+       "[source](https://github.com/kaiguender/dddex/blob/main/dddex/loadData.py#L24){target=\"_blank\" style=\"float:right; font-size:smaller\"}\n",
        "\n",
        "### loadDataYaz\n",
        "\n",
@@ -102,7 +102,7 @@
       "text/markdown": [
        "---\n",
        "\n",
-       "[source](https://github.com/kaiguender/dddex/blob/main/dddex/loadData.py#L99){target=\"_blank\" style=\"float:right; font-size:smaller\"}\n",
+       "[source](https://github.com/kaiguender/dddex/blob/main/dddex/loadData.py#L102){target=\"_blank\" style=\"float:right; font-size:smaller\"}\n",
        "\n",
        "### add_lag_features\n",
        "\n",
@@ -136,7 +136,7 @@
       "text/plain": [
        "---\n",
        "\n",
-       "[source](https://github.com/kaiguender/dddex/blob/main/dddex/loadData.py#L99){target=\"_blank\" style=\"float:right; font-size:smaller\"}\n",
+       "[source](https://github.com/kaiguender/dddex/blob/main/dddex/loadData.py#L102){target=\"_blank\" style=\"float:right; font-size:smaller\"}\n",
        "\n",
        "### add_lag_features\n",
        "\n",