Base Model für CITT erstellt, PTM Dortmund ergänzt, Tests hinzugefügt

2023-02-28 13:56:11 +01:00
parent b248a7e9b1
commit e861dbf10e
17 changed files with 917 additions and 103 deletions
--- a/.gitignore
+++ b/.gitignore
@@ -0,0 +1,180 @@
+temp
+.DS_Store
+
+
+# ---> Python
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# ---> VisualStudioCode
+.vscode/*
+!.vscode/settings.json
+!.vscode/tasks.json
+!.vscode/launch.json
+!.vscode/extensions.json
+!.vscode/*.code-snippets
+
+# Local History for Visual Studio Code
+.history/
+
+# Built Visual Studio Code Extensions
+*.vsix
+
--- a/debug.csv
+++ b/debug.csv
@@ -0,0 +1,4 @@
+,fit_F_amp,fit_F_freq,fit_F_phase,fit_F_offset,fit_F_slope,fit_F_r2,fit_F_max,fit_F_min,f,sigma,fit_s_hor_sum_amp,fit_s_hor_sum_freq,fit_s_hor_sum_phase,fit_s_hor_sum_offset,fit_s_hor_sum_slope,fit_s_hor_sum_r2,fit_s_hor_sum_max,fit_s_hor_sum_min,fit_s_hor_1_amp,fit_s_hor_1_freq,fit_s_hor_1_phase,fit_s_hor_1_offset,fit_s_hor_1_slope,fit_s_hor_1_r2,fit_s_hor_1_max,fit_s_hor_1_min,fit_s_hor_2_amp,fit_s_hor_2_freq,fit_s_hor_2_phase,fit_s_hor_2_offset,fit_s_hor_2_slope,fit_s_hor_2_r2,fit_s_hor_2_max,fit_s_hor_2_min,nu,E
+0,1162.037522728264,0.09999816445250176,3.2731742438169205,1657.4959341169797,0.022890975975805593,0.9999709812370754,2822.8786686693848,498.4860405788809,0.1,0.2,0.004904662057765795,0.09994473426198426,3.274570732678786,0.004472897149678457,3.4796345898322193e-06,0.9995438125784065,0.009632119781608398,-0.00042915385165576136,0.0022048443407161134,0.0999473113711256,3.2789165848392394,0.002036487114427019,1.317283541472095e-06,0.9992245191638016,0.0043773692868893654,-0.00022888205421645047,0.0026998634649033275,0.0999425971739857,3.271026693390654,0.00243640933189622,2.1623427295265008e-06,0.9993713553565571,0.005254750494719032,-0.0002479555587344695,0.2983926664681502,2260.236445571626
+1,1163.9861551163267,0.29999672326752724,3.271466866301432,1657.5773060905333,0.023592068619978698,0.999977491807627,2827.1702071859427,492.85935674606014,0.30003,0.2,0.004904630239776472,0.30002953724325576,3.261420279897325,0.004476978416102744,2.2128929628375675e-05,0.9997651921759285,0.009765634313234614,-0.0004482273561737665,0.0021960586065051407,0.300085988714776,3.2617587973425652,0.0020390391186955238,8.035203621628222e-06,0.9992996273163816,0.004420284672054908,-0.0002098085496983204,0.0027085993503841803,0.29998369085814713,3.2611491963027257,0.002437939646841411,1.4093566880537998e-05,0.9995179610005985,0.005354886393438715,-0.0002384188064754461,0.2983926664681502,2264.0413462626584
+2,1173.2940951101361,3.0019781539143713,3.1127799064755783,1652.6775323274487,2.2793532011736803,0.9997118511163391,2828.2192499344346,494.76670719786375,3.003,0.2,0.004927618845400971,3.0012837674744888,3.1051127487990566,0.004715737141843021,-1.2305236334063097e-05,0.998488708969846,0.009899148844860886,-0.0004005435948787328,0.0022065238872148044,3.0014146858816817,3.110359353742398,0.0021183309358349563,-8.842607057128579e-06,0.9965020191798836,0.004558567579810768,-0.00018119829292129186,0.002721172122260612,3.0011630113467382,3.100932209486545,0.00259739494570079,-3.4648940648246214e-06,0.9979287207765057,0.0054359487876403795,-0.000257492310993479,0.2983926664681502,2271.499199111919
--- a/src/paveit/init.py
+++ b/src/paveit/init.py
@@ -1,4 +1,5 @@
 # main __init__.py
 from .analysis import *
+from .functions import *
 from .helper import *
 from .labtest import *
--- a/src/paveit/functions/init.py
+++ b/src/paveit/functions/init.py
@@ -0,0 +1 @@
+from .citt import *
--- a/src/paveit/functions/citt.py
+++ b/src/paveit/functions/citt.py
@@ -0,0 +1,16 @@
+import numpy as np
+
+
+def stiffness_tp26(T, f, Emax, Emin, phi, z0, z1, T0=20.0):
+
+    alphaT = np.exp(phi * ((1 / (T + 273.15)) - (1 / (T0 + 273.15))))
+    x = np.log(f * alphaT) / np.log(10)
+    E = Emin + (Emax - Emin) / (1 + np.exp(z0 * x + z1))
+
+    return E
+
+
+def calc_nu(T):
+    #TODO: Prüfen ob Formel stimmt!
+    nu = 0.15 + (0.35) / (1 + np.exp(3.1849 - 0.04233 * (9 / 5 * T + 32)))
+    return nu
--- a/src/paveit/helper/init.py
+++ b/src/paveit/helper/init.py
@@ -1,6 +1,8 @@
+from .filehandling import read_file_to_bytesio
 from .filehasher import calc_hash_of_bytes
 from .minio import get_minio_client_archive, get_minio_client_processing

-__all__ = ['get_minio_client_archive', 'get_minio_client_processing',
+__all__ = ['read_file_to_bytesio',
+               'get_minio_client_archive', 'get_minio_client_processing',
                'calc_hash_of_bytes'
           ]
--- a/src/paveit/helper/filehandling.py
+++ b/src/paveit/helper/filehandling.py
@@ -0,0 +1,12 @@
+import logging
+from io import BytesIO
+
+logger = logging.getLogger(__name__)
+
+
+def read_file_to_bytesio(filename: str):
+    
+    with open(filename, "rb") as fh:
+        buf = BytesIO(fh.read())
+    
+    return buf
--- a/src/paveit/labtest/base.py
+++ b/src/paveit/labtest/base.py
@@ -1,90 +1,404 @@
 # coding: utf-8
 import io
+import logging

+import numpy as np
 import pandas as pd
+from paveit.analysis import fit_cos
+from paveit.functions import calc_nu
 from paveit.helper import calc_hash_of_bytes, get_minio_client_processing

-from worker import app, logger
-

 class DataSineLoad():
    """
    Base class for lab tests with sine load
    
    """
-    
-    def __init__(self, filename:str , metadata: dict):
+
+    def __init__(self,
+                 filename: str,
+                 metadata: dict,
+                 archive: bool = True,
+                 debug: bool = False,
+                 data: None | io.BytesIO = None):
        self.filename = filename
        self.metadata = metadata
+
+        if isinstance(data, io.BytesIO):
+            self.data = data
+
+        self.archive_data = archive
+        self.debug = debug
+
+        self._logger = logging.getLogger(__name__)
+
+        self._logger.info(
+            f'filename s3: {self.filename}, metadata: {self.metadata}')
+
+        self._pre_run()
+
+    def _set_parameter(self):
+
+        self.split_data_based_on_parameter = ['T', 'sigma', 'f']
+
+        self.col_as_int = ['N']
+        self.col_as_float = ['T', 'F', 's_piston', 's_hor_1', 'f', 's_hor_1', 's_hor_2']
+
+        self.val_col_names = ['time', 'T', 'f', 'sigma', 'N', 'F', 's_hor_1', 's_hor_2']
        
-        self._logger = logger
-        
-        self._logger.info(f'filename s3: {self.filename}, metadata: {self.metadata}')
+        self.columns_analyse = ['F','s_hor_sum','s_hor_1','s_hor_2','s_piston']
        
+        # Header names after standardization; check if exists
+        self.val_header_names = ['speciment_height', 'speciment_diameter']
+
+        self.number_of_load_cycles_for_analysis = 5
+
+        self.meta_names_of_parameter = {
+            'sigma': ['Max. Spannung']
+        }  #list of names
        
+        self.data_column_names = {
+            'time': ['Time Series'],
+            'F': ['Load Series'],
+            's_hor_1': ['LVDT1 Series'],
+            's_hor_2': ['LVDT2 Series'],
+        }
+
+    def update_parameter():
+        """ update standard prameter from function self._set_parameter()"""
+        pass
+
+    def _define_units(self):
+
+        self.unit_s = 1  #mm
+        self.unit_F = 1  #N
+        self.unit_t = 1 / 1000.  #s
+
    def _connect_to_s3(self):
        self._logger.info('connect to db')
-        
+
        self.__minioClient = get_minio_client_processing()
-        
+
    def _read_from_s3_to_bytesio(self):
        self._logger.info('read bytes')
-        
-        
+
        try:
            self._connect_to_s3()
-            response = self.__minioClient.get_object('processing', self.filename)
-            self.data = response.data            
+            response = self.__minioClient.get_object('processing',
+                                                     self.filename)
+            self.data = response.data
        finally:
            response.close()
            response.release_conn()
-        
-        
+
        self.data = io.BytesIO(self.data)
-        
+
    def _calc_hash_of_bytesio(self):
-        
+
        self.filehash = calc_hash_of_bytes(self.data)
        self.data.seek(0)
        self._logger.debug(f'Hash of file: {self.filehash}')
+
+    def _process_data(self):
+        
+        """ convert self.data (BytesIO) to pandas.DataFrame, update
+        self.metadata with informations from file """
+        
+        self._logger.debug('convert bytes to pandas.DataFrame')
+
+        encoding = 'utf-8'
+        self.data = pd.read_csv(self.data, encoding=encoding)
+
+    def _standardize_data(self):
+        
+        colnames = list(self.data.columns)
+        
+        for par, names in self.data_column_names.items():
+            for name in names:
+                colnames = [sub.replace(name, par) for sub in colnames]
+
+        self.data.columns = colnames
+        
+        print(self.data.head(5))
        

-    def _bytes_to_df(self):
-        self._logger.debug('convert bytes to pandas.DataFrame')
-                
-        encoding='utf-8'
-        self.df = pd.read_csv(self.data, encoding=encoding)
+    def _standardize_meta(self):
+        
+        for par, names in self.meta_names_of_parameter.items():
+            for name in names:
+                if name in self.metadata:
+                    
+                    self.metadata[par] = self.metadata[name]
+                    self.metadata.pop(name)
+                    
+                    break
+                    
+    def _validate_data(self):

-    def _calc(self): 
-        self._logger.debug('calc data')
-        return self.df.mean().mean()
+        for name in self.val_col_names:
+            if not name in self.data.columns:
+                raise
+    
+
+    def _validate_meta(self):
+        for name in self.val_header_names:
+            if not name in self.metadata:
+                raise
+
+    def _post_apply_units(self):
+
+        for col in ['s_hor_sum', 's_hor_1', 's_hor_2']:
+            if col in self.data.columns:
+                self.data[col] = self.data[col].mul(self.unit_s)
+
+        for col in ['F']:
+            self.data[col] = self.data[col].mul(self.unit_F)
+
+        for col in ['time']:
+            self.data[col] = self.data[col].mul(self.unit_t)
+
+        return True
+
+    def _post_select_importent_columns(self):
+        
+        # TODO: add more columns, check datamodel
+        
+        self.data = self.data[self.val_col_names]
+        
+
+    def _post_calc_missiong_values(self):
+        
+
+        cols = self.data.columns
+
+        if not 's_hor_sum' in cols:
+            self.data['s_hor_sum'] = self.data[['s_hor_1',
+                                                's_hor_2']].sum(axis=1)
+
+    def _post_opt_data(self):
+        #set dtypes:
+        for col in self.col_as_int:
+            self.data[col] = self.data[col].astype('int')
+        for col in self.col_as_float:
+            try:
+                self.data[col] = self.data[col].astype('float')
+            except:
+                pass
+
+        #set index
+        self.data = self.data.set_index('time')
+
+        return True
+
+    def _fit_split_data(self):
+        
+        data_gp = self.data.groupby(self.split_data_based_on_parameter)
+
+        data_list = []
+
+        for idx, d in data_gp:
+
+            idx_diff = np.diff(d.index)
+            dt_mean = idx_diff.mean()
+
+            gaps = idx_diff > (4 * dt_mean)
+            has_gaps = any(gaps)
+
+            if has_gaps == False:
+                data_list.append(d)
+
+            else:
+
+                #FIX: GAP FINDING
+                data_list.append(d)
+                """
+                print('has gaps')
+                print(gaps)
+                idx_gaps = (np.where(gaps)[0] - 1)[0]
+                print(idx_gaps)
+                data_list.append(d.iloc[0:idx_gaps])
+                """
+
+        #add self.
+        if len(data_list) == 0:
+            self.num_tests = 0
+            self.data = data_list[0]
+
+        else:
+            self.num_tests = len(data_list)
+            self.data = data_list
+            #break
+
+    def _fit_select_data(self):
+        """ 
+        select N load cycles from original data 
+        (a): Based on window of TP-Asphalt
+        (b) last N cycles
+        
+        """
+        
+        def sel_df(df, num=5):
+            
+            N = df['N'].unique()
+            freq = float(df['f'].unique()[0])
+
+            # define cycles to select
+            if freq == 10.0:
+                Nfrom = 98
+                Nto = 103
+            elif freq == 5.0:
+                Nfrom = 93
+                Nto = 97
+            elif freq == 3.0:
+                Nfrom = 43
+                Nto = 47
+            elif freq == 1.0:
+                Nfrom = 13
+                Nto = 17
+            elif freq == 0.3:
+                Nfrom = 8
+                Nto = 12
+            elif freq == 0.1:
+                Nfrom = 3
+                Nto = 7
+            else:
+                Nfrom = None
+                Nto = None
+            
+                
+            # Fall 1: nicht alle LW in Datei
+            if (max(N) < Nto) & (len(N) >= num):
+                df_sel = df[(df['N'] >= N[-num]) & (df['N'] <= N[-1])]
+            
+            # Fall 2:
+            else:
+
+                if Nfrom != None:
+                    if len(N) > Nto - Nfrom:
+                        df_sel = df[(df['N'] >= Nfrom) & (df['N'] <= Nto)]
+                        
+            return df_sel
+            
+        if not isinstance(self.data, list):
+            if self.number_of_load_cycles_for_analysis > 1:
+                df_sel = [
+                    sel_df(self.data,
+                           num=self.number_of_load_cycles_for_analysis)
+                ]
+            else:
+                df_sel = [self.data]
+
+        else:
+            df_sel = []
+            for d in self.data:
+                if self.number_of_load_cycles_for_analysis > 1:
+                    d_sel = sel_df(d,num=self.number_of_load_cycles_for_analysis)
+                else:
+                    d_sel = d
+
+                df_sel.append(d_sel)
+
+        # replace data
+        self.data = df_sel
+        
+    def _calc(self):
+
+        print(len(self.data))
+        
+        self.fit = []
+        for idx_data, data in enumerate(self.data):
+            
+            if data is None: continue
+            if len(data) < 10: continue
+            
+
+            data.index = data.index - data.index[0]
+            
+            res_temp = {}
+
+            x = data.index.values
+            
+            freq = np.round(float(data['f'].unique()),2)
+            sigma = float(data['sigma'].unique())
+            temperature = float(data['T'].unique())
+            
+            for idxcol, col in enumerate(self.columns_analyse):
+
+                if not col in data.columns: continue
+                y = data[col].values
+                
+                res = fit_cos(x,y, freq=freq)
+                
+                for key, value in res.items():
+                    res_temp[f'fit_{col}_{key}'] = value
+                
+                res_temp[f'fit_{col}_max'] = max(y)
+                res_temp[f'fit_{col}_min'] = min(y)
+
+                res_temp['f'] = freq
+                res_temp['sigma'] = sigma
+                res_temp['T'] = temperature
+
+            ## Stiffness
+            deltaF = res_temp['fit_F_amp']
+            nu = calc_nu(temperature)
+            res_temp['nu'] = nu
+            
+            h = float(self.metadata['speciment_height'])
+            
+            deltaU = res_temp['fit_s_hor_sum_amp']
+
+            res_temp['E'] = (deltaF * (0.274 + nu)) / (h * deltaU)
+
+            self.fit.append(res_temp)
+
+        self.fit = pd.DataFrame.from_records(self.fit)
+        
+        self.fit = self.fit.set_index(['T', 'f', 'sigma'])
+        
+        print(self.fit)
+        
        
    def _archive_binary_data(self):
-        
-        self._logger.debug('send file to archive')
-        app.send_task('ArchiveFile', args=[self.filename, 
-                                           self.metadata,
-                                           self.filehash,
-                                           'org',
-                                           'citt'
-                                           ],
-                      queue='archive'
-                      )
-        
-        

-    
+        self._logger.debug('send file to archive')
+        app.send_task(
+            'ArchiveFile',
+            args=[self.filename, self.metadata, self.filehash, 'org', 'citt'],
+            queue='archive')
+
+    def _pre_run(self):
+
+        if not hasattr(self, 'data'):
+            self._read_from_s3_to_bytesio()
+
+        self._calc_hash_of_bytesio()
+        self._set_parameter()
+        self.update_parameter()
+        self._define_units()
+
    def run(self):
        self._logger.info('run task')
-        self._read_from_s3_to_bytesio()
-        self._calc_hash_of_bytesio()
-        
-        self._bytes_to_df()
-        
-        res = self._calc()
-        self._logger.debug(f'results: {res}')
-        
-        self._archive_binary_data()
-        
-        return res
-    
+
+        self._process_data()
+
+        self._standardize_data()
+        self._standardize_meta()
+        self._validate_data()
+        self._validate_meta()
+
+        self._post_select_importent_columns()
+        self._post_apply_units()
+        self._post_calc_missiong_values()
+        self._post_opt_data()
+
+        self._fit_split_data()
+        self._fit_select_data()
+
+        self._calc()
+        #self._logger.debug(f'results: {res}')
+
+        #if self.archive_data:
+        #    self._archive_binary_data()
+
+        #return res
--- a/src/paveit/labtest/citt.py
+++ b/src/paveit/labtest/citt.py
@@ -5,6 +5,7 @@ from csv import reader
 import numpy as np
 import pandas as pd
 from paveit.labtest import DataSineLoad
+from torch import isin


 class CITTBase(DataSineLoad):
@@ -15,9 +16,9 @@ class CITT_KIT(DataSineLoad):
    def _calc(self):
        return (self.df.mean().mean(), self.df.max().max())

-    def _bytes_to_df(self):
+    def _process_data(self):
        logger.debug('convert bytes to pandas.DataFrame')
-        
+
        self.data.seek(0)
        with io.TextIOWrapper(self.data, encoding='latin-1') as read_obj:
            csv_reader = reader(read_obj, delimiter=';')
@@ -93,29 +94,50 @@ class CITT_KIT(DataSineLoad):
        #res = res.sort_values(['f', 'ZEIT'])

        #define in class
-        self.df = res.reset_index()
-        
-class CITT_PTMDortmund(DataSineLoad):
-    def _calc(self):
-        return (self.df.mean().mean(), self.df.max().max())
+        self.data = res.reset_index()

-    def _bytes_to_df(self):
+class CITT_PTMDortmund(DataSineLoad):
+    
+    def _define_units(self):
+
+        self.unit_s = 1  #mm
+        self.unit_F = 1000.  #N
+        self.unit_t = 1.  #s
+
+    def update_parameter(self):
+
+        self.meta_names_of_parameter = {'sigma': ['Max. Spannung', 'Max Stress'],
+                                                                       'f': ['Frequenz', 'Frequency'],
+                                                                       'T': ['Versuchstemperatur', 'Target Test Temperature'], 
+                                                                       'Nfrom': ['Erster Aufzeichnungslastwechsel', 'Start Cycle'],
+                                                                       'Nto': ['Letzer Aufzeichnungslastwechsel', 'Last Cycle'],
+                                                                       't': ['Zeitfolgen', 'Time Series'],
+                                                                       'speciment_diameter': ['Durchmesser (mm)', 'Diameter (mm)'],
+                                                                       'speciment_height': ['Länge (mm)', 'Length (mm)'],
+                                                                    } #list of names
+
+        self.data_column_names = {
+            'time': ['Time Series'],
+            'F': ['Load Series'],
+            's_hor_1': ['LVDT1 Series'],
+            's_hor_2': ['LVDT2 Series'],
+        }
+
+    def _process_data(self):
        res = []
-        
+
        xl = pd.ExcelFile(self.data)
        num_sheets = len(xl.sheet_names)
-        
-        print(num_sheets)
-        
+
        diameter = []
        height = []
-        
+

        for sheetid in range(num_sheets):
            temp = pd.read_excel(self.data, sheetid, skiprows=97)
            temp = temp.drop(index=0)
-                
-            #convert data to numerical data            
+
+            #convert data to numerical data
            for col in temp.columns:
                temp[col] = pd.to_numeric(temp[col])

@@ -124,53 +146,118 @@ class CITT_PTMDortmund(DataSineLoad):

            meta = pd.read_excel(self.data, sheetid,
                                      skiprows=1,
-                                      nrows=90)
+                                      nrows=80)

            meta = meta[meta.columns[[0, 2]]]
            meta = meta.set_index(
-                meta.columns[0]).to_dict()[meta.columns[1]]
+                meta.columns[0])
            
-            temp['sigma'] = float(meta['Max. Spannung'])
-            temp['T'] = float(meta['Versuchstemperatur'])
-            freq = float(meta['Frequenz'])
-            dt = 1 / freq
-            temp['f'] = freq
+            meta = meta.dropna(axis=0)
+            meta = meta[meta.columns[0]]
+            
+            meta = meta.to_dict()
+            
+            #remove whitespace in dict keys:
+            meta = {x.strip(): v for x, v in meta.items() if isinstance(x, str)}

-            Nfrom = int(meta['Erster Aufzeichnungslastwechsel'])
-            Nto = int(meta['Letzer Aufzeichnungslastwechsel'])
+            frequency_test = None
+            # add metadata to dataframe
+            for par in ['sigma', 'f', 'T']:
+                names = self.meta_names_of_parameter[par]
+                v = None
+                for name in names:
+                    try:
+                        v = np.round(float(meta[name]),5)
+                        
+                        if par == 'f':
+                            v = np.round(v,2)
+                        
+                        break
+                    except:
+                        pass
+                
+                assert v is not None
+                temp[par] = v
+                
+                if par == 'f':
+                    frequency_test = v
+                
+            # read additional parameters
+            names = self.meta_names_of_parameter['Nfrom']
+            for name in names:
+                try:
+                    Nfrom = int(meta[name])
+                    break
+                except:
+                    Nfrom = None
+            assert Nfrom is not None
+            
+            names = self.meta_names_of_parameter['Nto']
+            for name in names:
+                try:
+                    Nto = int(meta[name])
+                    break
+                except:
+                    Nto = None
+            assert Nto is not None

            #add cycle number to dataframe
-            time_idx = temp['Zeitfolgen'].values
-            N = np.zeros_like(time_idx)
-            self._logger.debug(len(N))
-            
+            names = self.meta_names_of_parameter['t']
+            for name in names:
+                try:
+                    time_idx = temp[name].values
+                    break
+                except:
+                    time_idx = None
+            assert time_idx is not None    
+                    
+            temp['N'] = 0
+
            self._logger.info(f'cycles from {Nfrom} to {Nto}')

            #BUG: Ist in Messdatei falsch definiert und wird von PTM angepasst.            '''
            #for cycle in range(Nfrom, Nto+1):
-            for cycle in range(10):
-                
+            
+            dt = 1.0/frequency_test
+            
+            tmax = dt
+            max_timeindex = max(time_idx)
+            
+            cycle = 0
+            while tmax < max_timeindex:
                # time window
-                tmin = (cycle) * dt
+                tmin = (cycle) * dt 
                tmax = (cycle + 1) * dt
-                
                #filter data
                idx = temp[(time_idx >= tmin)
                           & (time_idx < tmax)].index
-                
-                #FIX: siehe bug oben
-                if any(idx)>=500:
-                    idx = idx[idx<500]
-                
+                                
                #set cycle number
-                N[idx] = cycle    
+                temp.loc[idx, 'N'] = cycle
+                
+                cycle += 1

-            temp['N'] = N
-                
            # add diameter and height to list
-            diameter.append(float(meta['Durchmesser (mm)']))
-            height.append(float(meta['Länge (mm)']))
-                
+            names = self.meta_names_of_parameter['speciment_diameter']
+            for name in names:
+                try:
+                    v = float(meta[name])
+                    break
+                except:
+                    v = None
+            assert v is not None
+            diameter.append(v)
+            
+            names = self.meta_names_of_parameter['speciment_height']
+            for name in names:
+                try:
+                    v = float(meta[name])
+                    break
+                except:
+                    v = None
+            assert v is not None
+            height.append(v)
+            
            #append data to final dataframe
            res.append(temp)

@@ -178,15 +265,18 @@ class CITT_PTMDortmund(DataSineLoad):
        res = pd.concat(res)

        # add data from speciment to metadata
+
+        #if not 'speciment_diameter' in self.metadata:
+        #    self.metadata['speciment_diameter'] = np.mean(diameter)
+        #if not 'speciment_height' in self.metadata:
+        #    self.metadata['speciment_height'] = np.mean(height)
+            
        
-        if not 'diameter' in self.metadata:
-            self.metadata['diameter'] = np.mean(diameter)
-        if not 'height' in self.metadata:
-            self.metadata['height'] = np.mean(height)
-        
+
        #define in class
-        self.df = res.reset_index()
-        
+        self.data = res.reset_index()
+        self.metadata.update(meta)
+
        # log infos
-        logger.debug(self.metadata)
-        logger.debug(self.df.head())
+        self._logger.debug(self.metadata)
+        self._logger.debug(self.data.head())
--- a/tests/init.py
+++ b/tests/init.py
--- a/tests/analysis/init.py
+++ b/tests/analysis/init.py
--- a/tests/analysis/citt_test.py
+++ b/tests/analysis/citt_test.py
@@ -0,0 +1,50 @@
+import logging
+import os
+
+import toml
+from src.paveit.helper import read_file_to_bytesio
+from src.paveit.labtest.citt import CITT_PTMDortmund
+
+logger = logging.getLogger(__name__)
+
+
+def test_base_class():
+    pass
+
+
+def test_citt_ptmdortmund():
+
+    data_path = 'tests/data/citt/PTM_Dortmund'
+
+    res_dict = toml.load(os.path.join(data_path, 'meta.toml'))
+    logger.info(res_dict)
+
+    for filename, meta in res_dict.items():
+
+        logger.info(f'run test on: {filename}, {meta}')
+
+        file = os.path.join(data_path, filename)
+
+        buf = read_file_to_bytesio(file)
+
+        metadata = {'org': 'pytest_ptm_dortmund'}
+
+        res = CITT_PTMDortmund(filename, metadata, archive=False,
+                               data=buf)
+        res.run()
+
+        fit = res.fit.reset_index()
+        
+        assert len(fit) == 5
+        
+        m = res_dict[filename]
+        
+        for col in ['F', 's_hor_sum', 's_hor_1', 's_hor_2']:
+            assert all(fit[f'fit_{col}_r2'] >= m['min_r2'])
+        
+        sel = fit[(fit['f']==10.0) & (fit['sigma']==0.2) & (fit['T']==20.0)].iloc[0]
+        
+        Emin = (1-m['max_diff'])*m['stiffness_10Hz']
+        Emax = (1+m['max_diff'])*m['stiffness_10Hz']
+        
+        assert Emin <= sel['E'] <= Emax
--- a/tests/analysis/sine_test.py
+++ b/tests/analysis/sine_test.py
@@ -0,0 +1,116 @@
+from random import uniform
+
+import numpy as np
+from paveit.analysis.regression import fit_cos, fit_cos_eval
+
+
+def fit(freq: float = 10,
+        ampl: float = 100.0,
+        offset: float = 20.0,
+        slope: float = 0.1,
+        phase: float = 0.05,
+        error: float = 0.001) -> None:
+
+    N: int = 5
+    num_samples_per_cycle: int = 50
+
+    t = np.linspace(0, N / freq, N * num_samples_per_cycle)
+    y = ampl * np.cos(2 * np.pi * freq * t + phase) + slope * t + offset
+
+    r = fit_cos(t, y)
+
+    error_min = (1 - error)
+    error_max = (1 + error)
+
+    # ampltude
+    rel_error = (r['amp'] / ampl)
+    assert error_min <= rel_error <= error_max
+
+    # offset
+    rel_error = (r['offset'] / offset)
+    assert error_min <= rel_error <= error_max
+
+    # slope
+    rel_error = (r['slope'] / slope)
+    assert error_min <= rel_error <= error_max
+
+    # phase
+    rel_error = (r['phase'] / phase)
+    assert error_min <= rel_error <= error_max
+
+    # freq
+    rel_error = (r['freq'] / freq)
+    assert error_min <= rel_error <= error_max
+
+
+def test_fit_simple_sine(ntest: int = 50) -> None:
+    """
+    fit a simple sine signal and evaluate amplitude
+    
+    error: percentage error of ampl, Error max 0.1 %
+    """
+
+    fit()
+
+    #run multiple tests with random parameters
+    for i in range(ntest):
+
+        fit(
+            ampl=uniform(1e-3, 1000),
+            offset=uniform(1e-3, 1),
+            slope=uniform(1e-5, 1),
+            phase=uniform(1e-5, 1),
+        )
+
+
+def fit_noise(freq: float = 10,
+              ampl: float = 100.0,
+              offset: float = 20.0,
+              slope: float = 0.1,
+              phase: float = 0.05,
+              noise_level: float = 0.01,
+              error: float = 0.01) -> None:
+
+    N: int = 5
+    num_samples_per_cycle: int = 50
+
+    t = np.linspace(0, N / freq, N * num_samples_per_cycle)
+    y = ampl * np.cos(2 * np.pi * freq * t + phase) + slope * t + offset
+    y_noise = np.random.normal(0, noise_level * ampl, len(t))
+
+    y = y + y_noise
+
+    r = fit_cos(t, y)
+
+    error_min = (1 - error)
+    error_max = (1 + error)
+
+    # ampltude
+    rel_error = (r['amp'] / ampl)
+    assert error_min <= rel_error <= error_max
+    
+    # freq
+    rel_error = (r['freq'] / freq)
+    assert error_min <= rel_error <= error_max
+
+
+def test_fit_simple_sine_with_noise(ntest: int = 50) -> None:
+    """
+    fit a simple sine signal and evaluate amplitude
+    
+    error: percentage error of ampl, Error max 0.1 %
+    """
+
+    fit_noise()
+
+    #run multiple tests with random parameters
+    for i in range(ntest):
+
+        fit_noise(
+            ampl=uniform(1e-3, 1000),
+            offset=uniform(1e-3, 1),
+            slope=uniform(1e-5, 1),
+            phase=uniform(1e-5, 1),
+            noise_level=uniform(0.01, 0.1),
+            error=0.02,
+        )
--- a/tests/data/citt/PTM_Dortmund/meta.toml
+++ b/tests/data/citt/PTM_Dortmund/meta.toml
@@ -0,0 +1,4 @@
+["sample_01.xlsm"]
+min_r2 = 0.993
+max_diff = 0.005 #%
+stiffness_10Hz = 2269.0 #MPa
--- a/tests/data/citt/PTM_Dortmund/sample_01.xlsm
+++ b/tests/data/citt/PTM_Dortmund/sample_01.xlsm
--- a/tests/helper/init.py
+++ b/tests/helper/init.py
--- a/tests/helper/filehandling_test.py
+++ b/tests/helper/filehandling_test.py
@@ -0,0 +1,24 @@
+import glob
+import logging
+import os
+
+from src.paveit.helper import read_file_to_bytesio
+
+logger = logging.getLogger(__name__)
+
+data_path = 'tests/data/citt/PTM_Dortmund'
+
+
+def test_read_file_compare_filesize():
+
+    files = glob.glob(os.path.join(data_path, '*.xlsm'))
+
+    for file in files:
+
+        file_stat = os.stat(file)
+        file_size = file_stat.st_size
+
+        buf = read_file_to_bytesio(file)
+        buf_size = buf.getbuffer().nbytes
+
+        assert file_size == buf_size