def test_gridzonemap(): """Check that zonemap can be merged automatically be default, and also that there is some API for supplying the zonemap directly as a dictionary""" eclfiles = EclFiles(DATAFILE) grid_geom = grid.gridgeometry2df(eclfiles, zonemap=None) default_zonemap = grid_geom["ZONE"] grid_no_zone = grid.gridgeometry2df(eclfiles, zonemap={}) assert "ZONE" not in grid_no_zone assert (grid.df(eclfiles, zonemap=None)["ZONE"] == default_zonemap).all() df_no_zone = grid.df(eclfiles, zonemap={}) assert "ZONE" not in df_no_zone df_custom_zone = grid.gridgeometry2df(eclfiles, zonemap={1: "FIRSTLAYER"}) assert "ZONE" in df_custom_zone assert set( df_custom_zone[df_custom_zone["K"] == 1]["ZONE"].unique()) == set( ["FIRSTLAYER"]) assert len(df_custom_zone) == len(grid_no_zone) df_bogus_zones = grid.gridgeometry2df(eclfiles, zonemap={999999: "nonexistinglayer"}) assert pd.isnull(df_bogus_zones["ZONE"]).all() # Test a custom "subzone" map via direct usage of merge_zone on an dataframe # where ZONE already exists: dframe = grid.df(eclfiles) subzonemap = {1: "SUBZONE1", 2: "SUBZONE2"} dframe = common.merge_zones(dframe, subzonemap, zoneheader="SUBZONE", kname="K") assert (dframe["ZONE"] == default_zonemap).all() assert set(dframe[dframe["K"] == 1]["SUBZONE"].unique()) == set( ["SUBZONE1"]) assert set(dframe[dframe["K"] == 2]["SUBZONE"].unique()) == set( ["SUBZONE2"]) assert len(dframe) == len(grid_no_zone)
def test_grid_df(): """Test that dataframe with INIT vectors and coordinates can be produced""" eclfiles = EclFiles(DATAFILE) grid_df = grid.df(eclfiles) assert isinstance(grid_df, pd.DataFrame) assert not grid_df.empty assert "PERMX" in grid_df assert "PORO" in grid_df assert "PORV" in grid_df assert "I" in grid_df assert "J" in grid_df assert "K" in grid_df assert "X" in grid_df assert "Y" in grid_df assert "Z" in grid_df assert "VOLUME" in grid_df # Check that PORV is sensible assert (abs(sum(grid_df["PORO"] * grid_df["VOLUME"] - grid_df["PORV"])) / sum(grid_df["PORV"]) < 0.00001)
def test_df(): """Test the df function""" eclfiles = EclFiles(REEK) # assert error.. with pytest.raises(TypeError): # pylint: disable=no-value-for-parameter grid.df() grid_df = grid.df(eclfiles) assert not grid_df.empty assert "I" in grid_df # From GRID assert "PORO" in grid_df # From INIT assert "SOIL" not in grid_df # We do not get RST unless we ask for it. grid_df = grid.df(eclfiles, vectors="*") assert "I" in grid_df # From GRID assert "PORO" in grid_df # From INIT assert "SOIL" not in grid_df # We do not get RST unless we ask for it. grid_df = grid.df(eclfiles, vectors=["*"]) assert "I" in grid_df # From GRID assert "PORO" in grid_df # From INIT assert "SOIL" not in grid_df # We do not get RST unless we ask for it. grid_df = grid.df(eclfiles, vectors="PRESSURE") assert "I" in grid_df assert "PRESSURE" not in grid_df # that vector is only in RST assert len(grid_df) == 35817 assert "VOLUME" in grid_df grid_df = grid.df(eclfiles, vectors=["PRESSURE"]) assert "I" in grid_df assert not grid_df.empty assert "PRESSURE" not in grid_df geometry_cols = len(grid_df.columns) grid_df = grid.df(eclfiles, vectors=["PRESSURE"], rstdates="last", stackdates=True) assert "PRESSURE" in grid_df assert len(grid_df.columns) == geometry_cols + 2 assert "DATE" in grid_df # Present because of stackdates grid_df = grid.df(eclfiles, vectors="PRESSURE", rstdates="last") assert "PRESSURE" in grid_df assert len(grid_df.columns) == geometry_cols + 1 grid_df = grid.df(eclfiles, vectors="PRESSURE", rstdates="last", dateinheaders=True) assert "PRESSURE" not in grid_df assert "PRESSURE@2001-08-01" in grid_df grid_df = grid.df( eclfiles, vectors=["PORO", "PRESSURE"], rstdates="all", stackdates=True ) assert "PRESSURE" in grid_df assert len(grid_df.columns) == geometry_cols + 3 assert "DATE" in grid_df assert len(grid_df["DATE"].unique()) == 4 assert not grid_df.isna().any().any() # Check that all but the dynamic data has been repeated: df1 = ( grid_df[grid_df["DATE"] == "2000-01-01"] .drop(["DATE", "PRESSURE"], axis=1) .reset_index(drop=True) ) df2 = ( grid_df[grid_df["DATE"] == "2000-07-01"] .drop(["PRESSURE", "DATE"], axis=1) .reset_index(drop=True) ) df3 = ( grid_df[grid_df["DATE"] == "2001-02-01"] .drop(["PRESSURE", "DATE"], axis=1) .reset_index(drop=True) ) df4 = ( grid_df[grid_df["DATE"] == "2001-08-01"] .drop(["PRESSURE", "DATE"], axis=1) .reset_index(drop=True) ) pd.testing.assert_frame_equal(df1, df2) pd.testing.assert_frame_equal(df1, df3) pd.testing.assert_frame_equal(df1, df4) grid_df = grid.df(eclfiles, vectors="PORO") assert "I" in grid_df assert "PORO" in grid_df assert len(grid_df) == 35817 assert "DATE" not in grid_df grid_df = grid.df(eclfiles, vectors="PORO", rstdates="all") assert "I" in grid_df assert "PORO" in grid_df assert "DATE" not in grid_df # (no RST columns, so no DATE info in the dataframe) # (warnings should be printed) grid_df = grid.df(eclfiles, vectors="PORO", rstdates="all", stackdates=True) assert "I" in grid_df assert "PORO" in grid_df assert "DATE" not in grid_df
def test_df2ecl(tmp_path): """Test if we are able to output include files for grid data""" eclfiles = EclFiles(REEK) grid_df = grid.df(eclfiles) fipnum_str = grid.df2ecl(grid_df, "FIPNUM", dtype=int) assert grid.df2ecl(grid_df, "FIPNUM", dtype="int", nocomments=True) == grid.df2ecl( grid_df, "FIPNUM", dtype=int, nocomments=True ) with pytest.raises(ValueError, match="Wrong dtype argument foo"): grid.df2ecl(grid_df, "FIPNUM", dtype="foo") assert "FIPNUM" in fipnum_str assert "-- Output file printed by ecl2df.grid" in fipnum_str assert "35817 active cells" in fipnum_str # (comment at the end) assert "35840 total cell count" in fipnum_str # (comment at the end) assert len(fipnum_str) > 100 fipnum_str_nocomment = grid.df2ecl(grid_df, "FIPNUM", dtype=int, nocomments=True) assert "--" not in fipnum_str_nocomment fipnum2_str = grid.df2ecl( grid_df, "FIPNUM", dtype=int, eclfiles=eclfiles, nocomments=True ) # This would mean that we guessed the correct global size in the first run assert fipnum_str_nocomment == fipnum2_str float_fipnum_str = grid.df2ecl(grid_df, "FIPNUM", dtype=float) assert len(float_fipnum_str) > len(fipnum_str) # lots of .0 in the string. fipsatnum_str = grid.df2ecl(grid_df, ["FIPNUM", "SATNUM"], dtype=int) assert "FIPNUM" in fipsatnum_str assert "SATNUM" in fipsatnum_str grid_df["FIPNUM"] = grid_df["FIPNUM"] * 3333 fipnum_big_str = grid.df2ecl(grid_df, "FIPNUM", dtype=int) assert "3333" in fipnum_big_str assert len(fipnum_big_str) > len(fipnum_str) os.chdir(tmp_path) grid.df2ecl(grid_df, ["PERMX", "PERMY", "PERMZ"], dtype=float, filename="perm.inc") assert Path("perm.inc").is_file() incstring = open("perm.inc").readlines() assert sum([1 for line in incstring if "PERM" in line]) == 6 assert grid.df2ecl(grid_df, ["PERMX"], dtype=float, nocomments=True) == grid.df2ecl( grid_df, ["PERMX"], dtype="float", nocomments=True ) # with pytest.raises(ValueError, match="Wrong dtype argument"): grid.df2ecl(grid_df, ["PERMX"], dtype=dict) with pytest.raises(ValueError): grid.df2ecl(grid_df, ["PERMRR"]) # Check when we have restart info included: gr_rst = grid.df(eclfiles, rstdates="all") fipnum_str_rst = grid.df2ecl(gr_rst, "FIPNUM", dtype=int, nocomments=True) assert fipnum_str_rst == fipnum_str_nocomment # When dates are stacked, there are NaN's in the FIPNUM column, # which should be gracefully ignored. gr_rst_stacked = grid.df(eclfiles, rstdates="all", stackdates=True) fipnum_str_rst = grid.df2ecl(gr_rst_stacked, "FIPNUM", dtype=int, nocomments=True) assert fipnum_str_rst == fipnum_str_nocomment # dateinheaders here will be ignored due to stackdates: pd.testing.assert_frame_equal( gr_rst_stacked, grid.df(eclfiles, rstdates="all", stackdates=True, dateinheaders=True), )
def df( eclfiles: EclFiles, region: str = None, rstdates: Optional[Union[str, datetime.date, List[datetime.date]]] = None, soilcutoff: float = 0.2, sgascutoff: float = 0.7, swatcutoff: float = 0.7, stackdates: bool = False, ) -> pd.DataFrame: """Produce a dataframe with pillar information This is the "main" function for Python API users Produces a dataframe with data for each I-J combination (in the column PILLAR), and if a region parameter is supplied, also pr. region. PORV is the summed porevolume of the pillar (in the region), VOLUME is bulk volume, and PORO is porevolume weighted porosity PERM columns contain unweighted value averages, use with caution. If a restart date is picked, then SWAT and SGAS will be used to compute volumes pr. phase, WATVOL, OILVOL and GASVOL. The columns with dynamic data will include the date in the column headers like SWAT@2009-01-01 Args: region: A parameter the pillars will be split on. Typically EQLNUM or FIPNUM. Set to empty string or None to avoid any region grouping. rstdates: Dates for which restart data is to be extracted. The string can be in ISO-format, or one of the mnenomics 'first', 'last' or 'all'. It can also be a list of datetime.date. soilcutoff: If not None, an oil-water contact will be estimated pr. pillar, based on the deepest cell with SOIL above the given cutoff. Value is put in column OWC. sgascuttof: If not None, a gas contact will be estimated pr pillar, based on the deepest cell with SGAS above the given cutoff. Value is put in column GOC. swatcutoff: OWC or GWC is only computed for pillars where at least one cell is above this value. stackdates: If true, a column called DATE will be added and data for all restart dates will be added in a stacked manner. """ # List of vectors we want, conservative in order to save memory and cputime: vectors = [] if region: vectors.append(region) vectors.extend(["POR*", "PERM*", "SWAT", "SGAS", "1OVERBO", "1OVERBG"]) grid_df = grid.df(eclfiles, rstdates=rstdates, vectors=vectors, dateinheaders=True) rstdates_iso = grid.dates2rstindices(eclfiles, rstdates)[2] grid_df["PILLAR"] = grid_df["I"].astype(str) + "-" + grid_df["J"].astype( str) logger.info("Computing pillar statistics") groupbies = ["PILLAR"] if region: if region not in grid_df: logger.warning("Region parameter %s not found, ignored", region) else: groupbies.append(region) grid_df[region] = grid_df[region].astype(int) for datestr in rstdates_iso: logger.info("Dynamic volumes for %s", datestr) volumes = compute_volumes(grid_df, datestr=datestr) grid_df = pd.concat([grid_df, volumes], axis="columns", sort=False) aggregators = { key: AGGREGATORS[key.split("@")[0]] for key in grid_df if key.split("@")[0] in AGGREGATORS } # Group over PILLAR and possibly regions: grouped = (grid_df.groupby(groupbies).agg(aggregators)).reset_index() # Compute correct pillar averaged porosity (from bulk) if "PORV" in grouped and "VOLUME" in grouped: grouped["PORO"] = grouped["PORV"] / grouped["VOLUME"] # Compute contacts: for datestr in rstdates_iso: if "SWAT@" + datestr in grid_df and ("SOIL@" + datestr in grid_df or "SGAS@" + datestr in grid_df): contacts = compute_pillar_contacts( grid_df, region=region, soilcutoff=soilcutoff, sgascutoff=sgascutoff, swatcutoff=swatcutoff, datestr=datestr, ) if not contacts.empty: grouped = pd.merge(grouped, contacts, how="left") if stackdates: return common.stack_on_colnames(grouped, sep="@", stackcolname="DATE", inplace=True) return grouped
def test_df(): """Test the df function""" eclfiles = EclFiles(DATAFILE) # assert error.. with pytest.raises(TypeError): # pylint: disable=no-value-for-parameter grid.df() grid_df = grid.df(eclfiles) assert not grid_df.empty assert "I" in grid_df # From GRID assert "PORO" in grid_df # From INIT assert "SOIL" not in grid_df # We do not get RST unless we ask for it. grid_df = grid.df(eclfiles, vectors="*") assert "I" in grid_df # From GRID assert "PORO" in grid_df # From INIT assert "SOIL" not in grid_df # We do not get RST unless we ask for it. grid_df = grid.df(eclfiles, vectors=["*"]) assert "I" in grid_df # From GRID assert "PORO" in grid_df # From INIT assert "SOIL" not in grid_df # We do not get RST unless we ask for it. grid_df = grid.df(eclfiles, vectors="PRESSURE") assert "I" in grid_df assert "PRESSURE" not in grid_df # that vector is only in RST assert len(grid_df) == 35817 assert "VOLUME" in grid_df grid_df = grid.df(eclfiles, vectors=["PRESSURE"]) assert "I" in grid_df assert not grid_df.empty assert "PRESSURE" not in grid_df geometry_cols = len(grid_df.columns) grid_df = grid.df(eclfiles, vectors=["PRESSURE"], rstdates="last", stackdates=True) assert "PRESSURE" in grid_df assert len(grid_df.columns) == geometry_cols + 2 assert "DATE" in grid_df # awaits stacking grid_df = grid.df(eclfiles, vectors="PRESSURE", rstdates="last") assert "PRESSURE" in grid_df assert len(grid_df.columns) == geometry_cols + 1 grid_df = grid.df(eclfiles, vectors="PRESSURE", rstdates="last", dateinheaders=True) assert "PRESSURE" not in grid_df assert "PRESSURE@2001-08-01" in grid_df grid_df = grid.df(eclfiles, vectors="PRESSURE", rstdates="all", stackdates=True) assert "PRESSURE" in grid_df assert len(grid_df.columns) == geometry_cols + 2 assert "DATE" in grid_df assert len(grid_df["DATE"].unique()) == 4 grid_df = grid.df(eclfiles, vectors="PORO") assert "I" in grid_df assert "PORO" in grid_df assert len(grid_df) == 35817 assert "DATE" not in grid_df grid_df = grid.df(eclfiles, vectors="PORO", rstdates="all") assert "I" in grid_df assert "PORO" in grid_df assert "DATE" not in grid_df # (no RST columns, so no DATE info in the daaframe) # (warnings should be printed) grid_df = grid.df(eclfiles, vectors="PORO", rstdates="all", stackdates=True) assert "I" in grid_df assert "PORO" in grid_df assert "DATE" not in grid_df
def test_df2ecl(tmpdir): """Test if we are able to output include files for grid data""" eclfiles = EclFiles(DATAFILE) grid_df = grid.df(eclfiles) fipnum_str = grid.df2ecl(grid_df, "FIPNUM", dtype=int) assert "FIPNUM" in fipnum_str assert "-- Output file printed by ecl2df.grid" in fipnum_str assert "35817 active cells" in fipnum_str # (comment at the end) assert "35840 total cell count" in fipnum_str # (comment at the end) assert len(fipnum_str) > 100 fipnum_str_nocomment = grid.df2ecl(grid_df, "FIPNUM", dtype=int, nocomments=True) assert "--" not in fipnum_str_nocomment fipnum2_str = grid.df2ecl(grid_df, "FIPNUM", dtype=int, eclfiles=eclfiles, nocomments=True) # This would mean that we guessed the correct global size in the first run assert fipnum_str_nocomment == fipnum2_str float_fipnum_str = grid.df2ecl(grid_df, "FIPNUM", dtype=float) assert len(float_fipnum_str) > len(fipnum_str) # lots of .0 in the string. fipsatnum_str = grid.df2ecl(grid_df, ["FIPNUM", "SATNUM"], dtype=int) assert "FIPNUM" in fipsatnum_str assert "SATNUM" in fipsatnum_str grid_df["FIPNUM"] = grid_df["FIPNUM"] * 3333 fipnum_big_str = grid.df2ecl(grid_df, "FIPNUM", dtype=int) assert "3333" in fipnum_big_str assert len(fipnum_big_str) > len(fipnum_str) tmpdir.chdir() grid.df2ecl(grid_df, ["PERMX", "PERMY", "PERMZ"], dtype=float, filename="perm.inc") assert os.path.exists("perm.inc") incstring = open("perm.inc").readlines() assert sum([1 for line in incstring if "PERM" in line]) == 6 with pytest.raises(ValueError): grid.df2ecl(grid_df, ["PERMRR"]) # Check when we have restart info included: gr_rst = grid.df(eclfiles, rstdates="all") fipnum_str_rst = grid.df2ecl(gr_rst, "FIPNUM", dtype=int, nocomments=True) assert fipnum_str_rst == fipnum_str_nocomment # When dates are stacked, there are NaN's in the FIPNUM column, # which should be gracefully ignored. gr_rst_stacked = grid.df(eclfiles, rstdates="all", stackdates=True) fipnum_str_rst = grid.df2ecl(gr_rst_stacked, "FIPNUM", dtype=int, nocomments=True) assert fipnum_str_rst == fipnum_str_nocomment