Skip to content

Commit

Permalink
Test to/from_string
Browse files Browse the repository at this point in the history 
Closes: #10
  • Loading branch information
@APN-Pucky
APN-Pucky committed Oct 13, 2024
1 parent aff863d commit 485d384
Show file tree
Hide file tree
Showing 11 changed files with 251 additions and 86 deletions.
46 changes: 29 additions & 17 deletions src/babyyoda/grogu/histo1d_v2.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,11 @@ class Bin:
d_sumwx2: float = 0.0
d_numentries: float = 0.0

def __post_init__(self):
assert (
self.d_xmin is None or self.d_xmax is None or self.d_xmin < self.d_xmax
)

########################################################
# YODA compatibilty code
########################################################
Expand Down Expand Up @@ -129,17 +134,17 @@ def xVariance(self):
def numEntries(self):
return self.d_numentries

def __eq__(self, other):
return (
isinstance(other, GROGU_HISTO1D_V2.Bin)
and self.d_xmin == other.d_xmin
and self.d_xmax == other.d_xmax
and self.d_sumw == other.d_sumw
and self.d_sumw2 == other.d_sumw2
and self.d_sumwx == other.d_sumwx
and self.d_sumwx2 == other.d_sumwx2
and self.d_numentries == other.d_numentries
)
# def __eq__(self, other):
# return (
# isinstance(other, GROGU_HISTO1D_V2.Bin)
# and self.d_xmin == other.d_xmin
# and self.d_xmax == other.d_xmax
# and self.d_sumw == other.d_sumw
# and self.d_sumw2 == other.d_sumw2
# and self.d_sumwx == other.d_sumwx
# and self.d_sumwx2 == other.d_sumwx2
# and self.d_numentries == other.d_numentries
# )

def __add__(self, other):
assert isinstance(other, GROGU_HISTO1D_V2.Bin)
Expand Down Expand Up @@ -302,8 +307,11 @@ def to_string(histo) -> str:
return f"{header}{stats}{underflow}\n{overflow}\n{legend}{bin_data}\n{footer}"

@classmethod
def from_string(cls, file_content: str, key: str = "") -> "GROGU_HISTO1D_V2":
def from_string(cls, file_content: str) -> "GROGU_HISTO1D_V2":
lines = file_content.strip().splitlines()
key = ""
if find := re.search(r"BEGIN YODA_HISTO1D_V2 (\S+)", lines[0]):
key = find.group(1)

# Extract metadata (path, title)
path = ""
Expand All @@ -322,7 +330,11 @@ def from_string(cls, file_content: str, key: str = "") -> "GROGU_HISTO1D_V2":
data_section_started = False

for line in lines:
if line.startswith("#"):
if line.startswith("BEGIN YODA_HISTO1D_V2"):
continue
if line.startswith("END YODA_HISTO1D_V2"):
break
if line.startswith("#") or line.isspace():
continue
if line.startswith("---"):
data_section_started = True
Expand All @@ -332,18 +344,18 @@ def from_string(cls, file_content: str, key: str = "") -> "GROGU_HISTO1D_V2":

values = re.split(r"\s+", line.strip())
if values[0] == "Underflow":
underflow = GROGU_HISTO1D_V2.Bin.from_string(line)
underflow = cls.Bin.from_string(line)
elif values[0] == "Overflow":
overflow = GROGU_HISTO1D_V2.Bin.from_string(line)
overflow = cls.Bin.from_string(line)
elif values[0] == "Total":
# ignore for now
pass
else:
# Regular bin
bins.append(GROGU_HISTO1D_V2.Bin.from_string(line))
bins.append(cls.Bin.from_string(line))

# Create and return the YODA_HISTO1D_V2 object
return GROGU_HISTO1D_V2(
return cls(
d_key=key,
d_path=path,
d_title=title,
Expand Down
31 changes: 19 additions & 12 deletions src/babyyoda/grogu/histo1d_v3.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -155,7 +155,9 @@ def from_string(cls, string: str) -> "GROGU_HISTO1D_V3.Bin":
def __post_init__(self):
self.d_type = "Histo1D"
# one more edge than bins, subtract 2 for underflow and overflow
assert len(self.d_edges) == len(self.d_bins) + 1 - 2
assert (
len(self.d_edges) == len(self.d_bins) + 1 - 2
), f"{len(self.d_edges)} != {len(self.d_bins)} + 1 - 2"

############################################
# YODA compatibilty code
Expand Down Expand Up @@ -238,8 +240,11 @@ def rebinXTo(self, edges: List[float]):
assert len(self.d_bins) == len(self.xEdges()) - 1 + 2

@classmethod
def from_string(cls, file_content: str, key: str = "") -> "GROGU_HISTO1D_V3":
def from_string(cls, file_content: str) -> "GROGU_HISTO1D_V3":
lines = file_content.strip().splitlines()
key = ""
if find := re.search(r"BEGIN YODA_HISTO1D_V3 (\S+)", lines[0]):
key = find.group(1)

# Extract metadata (path, title)
path = ""
Expand All @@ -258,7 +263,11 @@ def from_string(cls, file_content: str, key: str = "") -> "GROGU_HISTO1D_V3":
data_section_started = False

for line in lines:
if line.startswith("#"):
if line.startswith("BEGIN YODA_HISTO1D_V3"):
continue
if line.startswith("END YODA_HISTO1D_V3"):
break
if line.startswith("#") or line.isspace():
continue
if line.startswith("---"):
data_section_started = True
Expand All @@ -267,17 +276,15 @@ def from_string(cls, file_content: str, key: str = "") -> "GROGU_HISTO1D_V3":
continue

if line.startswith("Edges"):
content = re.findall(r"\[(.*?)\]", line)
numbers_as_strings = re.findall(
r"[-+]?\d*\.\d+e[+-]?\d+|\d+", content[0]
)
edges = [float(i) for i in numbers_as_strings]
content = re.findall(r"\[(.*?)\]", line)[0]
values = re.split(r"\s+", content.replace(",", ""))
edges = [float(i) for i in values]
continue

bins.append(GROGU_HISTO1D_V3.Bin.from_string(line))
bins.append(cls.Bin.from_string(line))

# Create and return the YODA_HISTO1D_V2 object
return GROGU_HISTO1D_V3(
return cls(
d_key=key,
d_path=path,
d_title=title,
Expand All @@ -303,8 +310,8 @@ def to_string(self):

edges = f"Edges(A1): [{', '.join(str(e) for e in self.d_edges)}]\n"
# Add the bin data
bin_data = "\n".join(GROGU_HISTO1D_V3.Bin.to_string(b) for b in self.bins())
bin_data = "\n".join(GROGU_HISTO1D_V3.Bin.to_string(b) for b in self.bins(True))

footer = "END YODA_HISTO1D_V3\n"

return f"{header}{stats}{edges}\n\n# sumW\t sumW2\t sumW(A1)\t sumW2(A1)\t numEntries\n{bin_data}\n{footer}"
return f"{header}{stats}{edges}# sumW\t sumW2\t sumW(A1)\t sumW2(A1)\t numEntries\n{bin_data}\n{footer}"
24 changes: 16 additions & 8 deletions src/babyyoda/grogu/histo2d_v2.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -205,14 +205,18 @@ def to_string(self) -> str:

legend = "# xlow\t xhigh\t ylow\t yhigh\t sumw\t sumw2\t sumwx\t sumwx2\t sumwy\t sumwy2\t sumwxy\t numEntries\n"
bin_data = "\n".join(b.to_string() for b in self.d_bins)
footer = "END YODA_HISTO2D_V2\n"
footer = "\nEND YODA_HISTO2D_V2\n"

return f"{header}{stats}{legend}{bin_data}{footer}"

@classmethod
def from_string(cls, file_content: str, name: str = "") -> "GROGU_HISTO2D_V2":
def from_string(cls, file_content: str) -> "GROGU_HISTO2D_V2":
lines = file_content.strip().splitlines()

key = ""
if find := re.search(r"BEGIN YODA_HISTO2D_V2 (\S+)", lines[0]):
key = find.group(1)

# Extract metadata (path, title)
path = ""
title = ""
Expand All @@ -229,7 +233,11 @@ def from_string(cls, file_content: str, name: str = "") -> "GROGU_HISTO2D_V2":
data_section_started = False

for line in lines:
if line.startswith("#"):
if line.startswith("BEGIN YODA_HISTO2D_V2"):
continue
if line.startswith("END YODA_HISTO2D_V2"):
break
if line.startswith("#") or line.isspace():
continue
if line.startswith("---"):
data_section_started = True
Expand All @@ -239,7 +247,7 @@ def from_string(cls, file_content: str, name: str = "") -> "GROGU_HISTO2D_V2":

values = re.split(r"\s+", line.strip())
if values[0] == "Underflow":
underflow = GROGU_HISTO2D_V2.Bin(
underflow = cls.Bin(
None,
None,
None,
Expand All @@ -254,7 +262,7 @@ def from_string(cls, file_content: str, name: str = "") -> "GROGU_HISTO2D_V2":
float(values[9]),
)
elif values[0] == "Overflow":
overflow = GROGU_HISTO2D_V2.Bin(
overflow = cls.Bin(
None,
None,
None,
Expand Down Expand Up @@ -286,7 +294,7 @@ def from_string(cls, file_content: str, name: str = "") -> "GROGU_HISTO2D_V2":
numEntries,
) = map(float, values)
bins.append(
GROGU_HISTO2D_V2.Bin(
cls.Bin(
xlow,
xhigh,
ylow,
Expand All @@ -302,8 +310,8 @@ def from_string(cls, file_content: str, name: str = "") -> "GROGU_HISTO2D_V2":
)
)

return GROGU_HISTO2D_V2(
d_key=name,
return cls(
d_key=key,
d_path=path,
d_title=title,
d_bins=bins,
Expand Down
31 changes: 19 additions & 12 deletions src/babyyoda/grogu/histo2d_v3.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -177,19 +177,24 @@ def to_string(self) -> str:
# f"# Mean: {self.mean()}\n"
# f"# Area: {self.area()}\n"
# )
edges = ""
for i, edg in enumerate(self.d_edges):
edges += f"Edges(A{i+1}): [{', '.join(str(e) for e in edg )}]\n"

legend = (
"# sumw\t sumw2\t sumwx\t sumwx2\t sumwy\t sumwy2\t sumwxy\t numEntries\n"
)
bin_data = "\n".join(b.to_string() for b in self.d_bins)
footer = "END YODA_HISTO2D_V3\n"
footer = "\nEND YODA_HISTO2D_V3\n"

return f"{header}{stats}{legend}{bin_data}{footer}"
return f"{header}{stats}{edges}{legend}{bin_data}{footer}"

@classmethod
def from_string(cls, file_content: str, key: str = "") -> "GROGU_HISTO2D_V3":
def from_string(cls, file_content: str) -> "GROGU_HISTO2D_V3":
lines = file_content.strip().splitlines()

key = ""
if find := re.search(r"BEGIN YODA_HISTO2D_V3 (\S+)", lines[0]):
key = find.group(1)
# Extract metadata (path, title)
path = ""
title = ""
Expand All @@ -207,7 +212,11 @@ def from_string(cls, file_content: str, key: str = "") -> "GROGU_HISTO2D_V3":
data_section_started = False

for line in lines:
if line.startswith("#"):
if line.startswith("BEGIN YODA_HISTO2D_V3"):
continue
if line.startswith("END YODA_HISTO2D_V3"):
break
if line.startswith("#") or line.isspace():
continue
if line.startswith("---"):
data_section_started = True
Expand All @@ -216,17 +225,15 @@ def from_string(cls, file_content: str, key: str = "") -> "GROGU_HISTO2D_V3":
continue

if line.startswith("Edges"):
content = re.findall(r"\[(.*?)\]", line)
numbers_as_strings = re.findall(
r"[-+]?\d*\.\d+e[+-]?\d+|\d+", content[0]
)
edges += [[float(i) for i in numbers_as_strings]]
content = re.findall(r"\[(.*?)\]", line)[0]
values = re.split(r"\s+", content.replace(",", ""))
edges += [[float(i) for i in values]]
continue

bins.append(GROGU_HISTO2D_V3.Bin.from_string(line))
bins.append(cls.Bin.from_string(line))

# Create and return the YODA_HISTO1D_V2 object
return GROGU_HISTO2D_V3(
return cls(
d_key=key,
d_path=path,
d_title=title,
Expand Down
14 changes: 8 additions & 6 deletions src/babyyoda/grogu/read.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -10,23 +10,25 @@ def read(file_path: str):
with open(file_path) as f:
content = f.read()

pattern = re.compile(r"BEGIN (YODA_[A-Z0-9_]+) ([^\n]+)\n(.*?)\nEND \1", re.DOTALL)
pattern = re.compile(
r"(BEGIN (YODA_[A-Z0-9_]+) ([^\n]+)\n(.*?)\nEND \2)", re.DOTALL
)
matches = pattern.findall(content)

histograms = {}

for hist_type, name, body in matches:
for full_match, hist_type, name, body in matches:
if hist_type == "YODA_HISTO1D_V2":
hist = GROGU_HISTO1D_V2.from_string(body, name)
hist = GROGU_HISTO1D_V2.from_string(full_match)
histograms[name] = hist
elif hist_type == "YODA_HISTO1D_V3":
hist = GROGU_HISTO1D_V3.from_string(body, name)
hist = GROGU_HISTO1D_V3.from_string(full_match)
histograms[name] = hist
elif hist_type == "YODA_HISTO2D_V2":
hist = GROGU_HISTO2D_V2.from_string(body, name)
hist = GROGU_HISTO2D_V2.from_string(full_match)
histograms[name] = hist
elif hist_type == "YODA_HISTO2D_V3":
hist = GROGU_HISTO2D_V3.from_string(body, name)
hist = GROGU_HISTO2D_V3.from_string(full_match)
histograms[name] = hist
else:
# Add other parsing logic for different types if necessary
Expand Down
2 changes: 1 addition & 1 deletion src/babyyoda/test.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -59,7 +59,7 @@ def assert_value1d(gb, yb):
assert gb.numEntries() == yb.numEntries()


def assert_equal_histo1d(gh1, yh1):
def assert_histo1d(gh1, yh1):
assert_ao(gh1, yh1)

assert len(gh1.bins()) == len(yh1.bins()), f"{len(gh1.bins())} != {len(yh1.bins())}"
Expand Down
Loading

0 comments on commit 485d384

Please sign in to comment.