chore(release): 0.6.6

Reviewed-on: #21

.gitignore

@@ -114,6 +114,10 @@ ENV/
 env.bak/
 venv.bak/
 
+# direnv
+.envrc
+.direnv
+
 # Spyder project settings
 .spyderproject
 .spyproject

CHANGELOG.md

@@ -2,6 +2,42 @@
 
 All notable changes to this project will be documented in this file. See [standard-version](https://github.com/conventional-changelog/standard-version) for commit guidelines.
 
+### [0.6.6](https://gitea.deepak.science:2222/physics/deepdog/compare/0.6.5...0.6.6) (2023-04-09)
+
+
+### Bug Fixes
+
+* removes bad logging in multiprocessing function ([8fd1b75](https://gitea.deepak.science:2222/physics/deepdog/commit/8fd1b75e1378301210bfa8f14dd09174bbd21414))
+
+### [0.6.5](https://gitea.deepak.science:2222/physics/deepdog/compare/0.6.4...0.6.5) (2023-04-09)
+
+
+### Features
+
+* adds temp aware guy using new pdme temp-flexible feature for bundling temp models ([de1ec3e](https://gitea.deepak.science:2222/physics/deepdog/commit/de1ec3e70062d418e0d4c89716905cc9313d2e26))
+
+### [0.6.4](https://gitea.deepak.science:2222/physics/deepdog/compare/0.6.3...0.6.4) (2022-08-13)
+
+
+### Features
+
+* Prints model names while running ([7ea1d71](https://gitea.deepak.science:2222/physics/deepdog/commit/7ea1d715f67e81c9fa841c5a62f1cc700ff7363d))
+
+### [0.6.3](https://gitea.deepak.science:2222/physics/deepdog/compare/0.6.2...0.6.3) (2022-06-12)
+
+
+### Features
+
+* adds fast filter variant ([2c5c122](https://gitea.deepak.science:2222/physics/deepdog/commit/2c5c1228209e51d17253f07470e2f1e6dc6872d7))
+* adds tester for fast filter real spectrum ([0a1a277](https://gitea.deepak.science:2222/physics/deepdog/commit/0a1a27759b0d4ab01da214b76ab14bf2b1fe00e3))
+
+### [0.6.2](https://gitea.deepak.science:2222/physics/deepdog/compare/0.6.1...0.6.2) (2022-05-26)
+
+
+### Features
+
+* adds better import api for real data run ([d7e0f13](https://gitea.deepak.science:2222/physics/deepdog/commit/d7e0f13ca55197b24cb534c80f321ee76b9c4a40))
+
 ### [0.6.1](https://gitea.deepak.science:2222/physics/deepdog/compare/0.6.0...0.6.1) (2022-05-22)
 
 

Jenkinsfile

@@ -4,7 +4,7 @@ pipeline {
 		label 'deepdog'  // all your pods will be named with this prefix, followed by a unique id
 		idleMinutes 5  // how long the pod will live after no jobs have run on it
 		yamlFile 'jenkins/ci-agent-pod.yaml'  // path to the pod definition relative to the root of our project
-		defaultContainer 'python'  // define a default container if more than a few stages use it, will default to jnlp container
+		defaultContainer 'poetry'  // define a default container if more than a few stages use it, will default to jnlp container
 	  }
 	}
 
@@ -12,36 +12,30 @@ pipeline {
 		parallelsAlwaysFailFast()
 	}
 
-	environment {
-		POETRY_HOME="/opt/poetry"
-		POETRY_VERSION="1.1.12"
-	}
-
 	stages {
 		stage('Build') {
 			steps {
 				echo 'Building...'
 				sh 'python --version'
-				sh 'curl -sSL https://raw.githubusercontent.com/python-poetry/poetry/master/get-poetry.py | python'
-				sh '${POETRY_HOME}/bin/poetry --version'
-				sh '${POETRY_HOME}/bin/poetry install'
+				sh 'poetry --version'
+				sh 'poetry install'
 			}
 		}
 		stage('Test') {
 			parallel{
 				stage('pytest') {
 					steps {
-						sh '${POETRY_HOME}/bin/poetry run pytest'
+						sh 'poetry run pytest'
 					}
 				}
 				stage('lint') {
 					steps {
-						sh '${POETRY_HOME}/bin/poetry run flake8 deepdog tests'
+						sh 'poetry run flake8 deepdog tests'
 					}
 				}
 				stage('mypy') {
 					steps {
-						sh '${POETRY_HOME}/bin/poetry run mypy deepdog'
+						sh 'poetry run mypy deepdog'
 					}
 				}
 			}
@@ -57,7 +51,7 @@ pipeline {
 			}
 			steps {
 				echo 'Deploying...'
-				sh '${POETRY_HOME}/bin/poetry publish -u ${PYPI_USR} -p ${PYPI_PSW} --build'
+				sh 'poetry publish -u ${PYPI_USR} -p ${PYPI_PSW} --build'
 			}
 		}
 

README.md

@@ -5,7 +5,7 @@
 [![Jenkins](https://img.shields.io/jenkins/build?jobUrl=https%3A%2F%2Fjenkins.deepak.science%2Fjob%2Fgitea-physics%2Fjob%2Fdeepdog%2Fjob%2Fmaster&style=flat-square)](https://jenkins.deepak.science/job/gitea-physics/job/deepdog/job/master/)
 ![Jenkins tests](https://img.shields.io/jenkins/tests?compact_message&jobUrl=https%3A%2F%2Fjenkins.deepak.science%2Fjob%2Fgitea-physics%2Fjob%2Fdeepdog%2Fjob%2Fmaster%2F&style=flat-square)
 ![Jenkins Coverage](https://img.shields.io/jenkins/coverage/cobertura?jobUrl=https%3A%2F%2Fjenkins.deepak.science%2Fjob%2Fgitea-physics%2Fjob%2Fdeepdog%2Fjob%2Fmaster%2F&style=flat-square)
-![Maintenance](https://img.shields.io/maintenance/yes/2022?style=flat-square)
+![Maintenance](https://img.shields.io/maintenance/yes/2023?style=flat-square)
 
 The DiPole DiaGnostic tool.
 

deepdog/__init__.py

@@ -2,6 +2,8 @@ import logging
 from deepdog.meta import __version__
 from deepdog.bayes_run import BayesRun
 from deepdog.bayes_run_simulpairs import BayesRunSimulPairs
+from deepdog.real_spectrum_run import RealSpectrumRun
+from deepdog.temp_aware_real_spectrum_run import TempAwareRealSpectrumRun
 
 
 def get_version():
@@ -12,6 +14,8 @@ __all__ = [
 	"get_version",
 	"BayesRun",
 	"BayesRunSimulPairs",
+	"RealSpectrumRun",
+	"TempAwareRealSpectrumRun",
 ]
 
 

deepdog/real_spectrum_run.py

@@ -32,6 +32,28 @@ def get_a_result(input) -> int:
 	return numpy.count_nonzero(pdme.util.fast_v_calc.between(vals, lows, highs))
 
 
+def get_a_result_fast_filter(input) -> int:
+	model, dot_inputs, lows, highs, monte_carlo_count, seed = input
+
+	rng = numpy.random.default_rng(seed)
+	# TODO: A long term refactor is to pull the frequency stuff out from here. The None stands for max_frequency, which is unneeded in the actually useful models.
+	sample_dipoles = model.get_monte_carlo_dipole_inputs(
+		monte_carlo_count, None, rng_to_use=rng
+	)
+
+	current_sample = sample_dipoles
+	for di, low, high in zip(dot_inputs, lows, highs):
+
+		if len(current_sample) < 1:
+			break
+		vals = pdme.util.fast_v_calc.fast_vs_for_dipoleses(
+			numpy.array([di]), current_sample
+		)
+
+		current_sample = current_sample[numpy.all((vals > low) & (vals < high), axis=1)]
+	return len(current_sample)
+
+
 class RealSpectrumRun:
 	"""
 	A bayes run given some real data.
@@ -65,6 +87,7 @@ class RealSpectrumRun:
 		max_monte_carlo_cycles_steps: int = 10,
 		chunksize: int = CHUNKSIZE,
 		initial_seed: int = 12345,
+		use_fast_filter: bool = True,
 	) -> None:
 		self.measurements = measurements
 		self.dot_inputs = [(measure.r, measure.f) for measure in self.measurements]
@@ -93,7 +116,11 @@ class RealSpectrumRun:
 		self.probabilities = [1 / self.model_count] * self.model_count
 
 		timestamp = datetime.datetime.now().strftime("%Y%m%d-%H%M%S")
-		self.filename = f"{timestamp}-{filename_slug}.realdata.bayesrun.csv"
+		self.use_fast_filter = use_fast_filter
+		ff_string = "no_fast_filter"
+		if self.use_fast_filter:
+			ff_string = "fast_filter"
+		self.filename = f"{timestamp}-{filename_slug}.realdata.{ff_string}.bayesrun.csv"
 		self.initial_seed = initial_seed
 
 	def go(self) -> None:
@@ -113,8 +140,10 @@ class RealSpectrumRun:
 
 		results = []
 		_logger.debug("Going to iterate over models now")
-		for model_count, model in enumerate(self.models):
-			_logger.debug(f"Doing model #{model_count}")
+		for model_count, (model, model_name) in enumerate(
+			zip(self.models, self.model_names)
+		):
+			_logger.debug(f"Doing model #{model_count}: {model_name}")
 			core_count = multiprocessing.cpu_count() - 1 or 1
 			with multiprocessing.Pool(core_count) as pool:
 				cycle_count = 0
@@ -133,9 +162,13 @@ class RealSpectrumRun:
 					# that way we get more stuff.
 					seeds = seed_sequence.spawn(self.monte_carlo_cycles)
 
+					if self.use_fast_filter:
+						result_func = get_a_result_fast_filter
+					else:
+						result_func = get_a_result
 					current_success = sum(
 						pool.imap_unordered(
-							get_a_result,
+							result_func,
 							[
 								(
 									model,

deepdog/temp_aware_real_spectrum_run.py

@@ -0,0 +1,225 @@
+import pdme.inputs
+import pdme.model
+import pdme.measurement
+import pdme.measurement.input_types
+import pdme.measurement.oscillating_dipole
+import pdme.util.fast_v_calc
+import pdme.util.fast_nonlocal_spectrum
+from typing import Sequence, Tuple, List, Dict, Union, Mapping
+import datetime
+import csv
+import multiprocessing
+import logging
+import numpy
+
+
+# TODO: remove hardcode
+CHUNKSIZE = 50
+
+
+_logger = logging.getLogger(__name__)
+
+
+def get_a_result_fast_filter(input) -> int:
+	# 								(
+	# 	model,
+	# 	self.dot_inputs_array_dict,
+	# 	low_high_dict,
+	# 	self.monte_carlo_count,
+	# 	seed,
+	# )
+	model, dot_inputs_dict, low_high_dict, monte_carlo_count, seed = input
+
+	rng = numpy.random.default_rng(seed)
+	# TODO: A long term refactor is to pull the frequency stuff out from here. The None stands for max_frequency, which is unneeded in the actually useful models.
+	sample_dipoles = model.get_monte_carlo_dipole_inputs(
+		monte_carlo_count, None, rng_to_use=rng
+	)
+
+	current_sample = sample_dipoles
+	for temp in dot_inputs_dict.keys():
+		dot_inputs = dot_inputs_dict[temp]
+		lows, highs = low_high_dict[temp]
+		for di, low, high in zip(dot_inputs, lows, highs):
+
+			if len(current_sample) < 1:
+				break
+			vals = pdme.util.fast_v_calc.fast_vs_for_asymmetric_dipoleses(
+				numpy.array([di]), current_sample, temp
+			)
+
+			current_sample = current_sample[
+				numpy.all((vals > low) & (vals < high), axis=1)
+			]
+	return len(current_sample)
+
+
+class TempAwareRealSpectrumRun:
+	"""
+	A bayes run given some real data, with potentially variable temperature.
+
+	Parameters
+	----------
+	measurements_dict : Dict[float, Sequence[pdme.measurement.DotRangeMeasurement]]
+	The dot inputs for this bayes run, in a dictionary indexed by temperatures
+
+	models_with_names : models_with_names: Sequence[Tuple[str, pdme.model.DipoleModel]],
+
+	The models to evaluate.
+
+	actual_model : pdme.model.DipoleModel
+	The model which is actually correct.
+
+	filename_slug : str
+	The filename slug to include.
+
+	run_count: int
+	The number of runs to do.
+	"""
+
+	def __init__(
+		self,
+		measurements_dict: Mapping[
+			float, Sequence[pdme.measurement.DotRangeMeasurement]
+		],
+		models_with_names: Sequence[Tuple[str, pdme.model.DipoleModel]],
+		filename_slug: str,
+		monte_carlo_count: int = 10000,
+		monte_carlo_cycles: int = 10,
+		target_success: int = 100,
+		max_monte_carlo_cycles_steps: int = 10,
+		chunksize: int = CHUNKSIZE,
+		initial_seed: int = 12345,
+	) -> None:
+		self.measurements_dict = measurements_dict
+		self.dot_inputs_dict = {
+			k: [(measure.r, measure.f) for measure in measurements]
+			for k, measurements in measurements_dict.items()
+		}
+
+		self.dot_inputs_array_dict = {
+			k: pdme.measurement.input_types.dot_inputs_to_array(dot_inputs)
+			for k, dot_inputs in self.dot_inputs_dict.items()
+		}
+
+		self.models = [model for (_, model) in models_with_names]
+		self.model_names = [name for (name, _) in models_with_names]
+		self.model_count = len(self.models)
+
+		self.monte_carlo_count = monte_carlo_count
+		self.monte_carlo_cycles = monte_carlo_cycles
+		self.target_success = target_success
+		self.max_monte_carlo_cycles_steps = max_monte_carlo_cycles_steps
+
+		self.csv_fields = []
+
+		self.compensate_zeros = True
+		self.chunksize = chunksize
+		for name in self.model_names:
+			self.csv_fields.extend([f"{name}_success", f"{name}_count", f"{name}_prob"])
+
+		# for now initialise priors as uniform.
+		self.probabilities = [1 / self.model_count] * self.model_count
+
+		timestamp = datetime.datetime.now().strftime("%Y%m%d-%H%M%S")
+		ff_string = "fast_filter"
+		self.filename = f"{timestamp}-{filename_slug}.realdata.{ff_string}.bayesrun.csv"
+		self.initial_seed = initial_seed
+
+	def go(self) -> None:
+		with open(self.filename, "a", newline="") as outfile:
+			writer = csv.DictWriter(outfile, fieldnames=self.csv_fields, dialect="unix")
+			writer.writeheader()
+
+		low_high_dict = {}
+		for temp, measurements in self.measurements_dict.items():
+			(
+				lows,
+				highs,
+			) = pdme.measurement.input_types.dot_range_measurements_low_high_arrays(
+				measurements
+			)
+			low_high_dict[temp] = (lows, highs)
+
+		# define a new seed sequence for each run
+		seed_sequence = numpy.random.SeedSequence(self.initial_seed)
+
+		results = []
+		_logger.debug("Going to iterate over models now")
+		for model_count, (model, model_name) in enumerate(
+			zip(self.models, self.model_names)
+		):
+			_logger.debug(f"Doing model #{model_count}: {model_name}")
+			core_count = multiprocessing.cpu_count() - 1 or 1
+			with multiprocessing.Pool(core_count) as pool:
+				cycle_count = 0
+				cycle_success = 0
+				cycles = 0
+				while (cycles < self.max_monte_carlo_cycles_steps) and (
+					cycle_success <= self.target_success
+				):
+					_logger.debug(f"Starting cycle {cycles}")
+					cycles += 1
+					current_success = 0
+					cycle_count += self.monte_carlo_count * self.monte_carlo_cycles
+
+					# generate a seed from the sequence for each core.
+					# note this needs to be inside the loop for monte carlo cycle steps!
+					# that way we get more stuff.
+					seeds = seed_sequence.spawn(self.monte_carlo_cycles)
+
+					result_func = get_a_result_fast_filter
+
+					current_success = sum(
+						pool.imap_unordered(
+							result_func,
+							[
+								(
+									model,
+									self.dot_inputs_array_dict,
+									low_high_dict,
+									self.monte_carlo_count,
+									seed,
+								)
+								for seed in seeds
+							],
+							self.chunksize,
+						)
+					)
+
+					cycle_success += current_success
+					_logger.debug(f"current running successes: {cycle_success}")
+				results.append((cycle_count, cycle_success))
+
+		_logger.debug("Done, constructing output now")
+		row: Dict[str, Union[int, float, str]] = {}
+
+		successes: List[float] = []
+		counts: List[int] = []
+		for model_index, (name, (count, result)) in enumerate(
+			zip(self.model_names, results)
+		):
+
+			row[f"{name}_success"] = result
+			row[f"{name}_count"] = count
+			successes.append(max(result, 0.5))
+			counts.append(count)
+
+		success_weight = sum(
+			[
+				(succ / count) * prob
+				for succ, count, prob in zip(successes, counts, self.probabilities)
+			]
+		)
+		new_probabilities = [
+			(succ / count) * old_prob / success_weight
+			for succ, count, old_prob in zip(successes, counts, self.probabilities)
+		]
+		self.probabilities = new_probabilities
+		for name, probability in zip(self.model_names, self.probabilities):
+			row[f"{name}_prob"] = probability
+		_logger.info(row)
+
+		with open(self.filename, "a", newline="") as outfile:
+			writer = csv.DictWriter(outfile, fieldnames=self.csv_fields, dialect="unix")
+			writer.writerow(row)

flake.lock

@@ -0,0 +1,95 @@
+{
+  "nodes": {
+    "flake-utils": {
+      "locked": {
+        "lastModified": 1648297722,
+        "narHash": "sha256-W+qlPsiZd8F3XkzXOzAoR+mpFqzm3ekQkJNa+PIh1BQ=",
+        "owner": "numtide",
+        "repo": "flake-utils",
+        "rev": "0f8662f1319ad6abf89b3380dd2722369fc51ade",
+        "type": "github"
+      },
+      "original": {
+        "owner": "numtide",
+        "repo": "flake-utils",
+        "rev": "0f8662f1319ad6abf89b3380dd2722369fc51ade",
+        "type": "github"
+      }
+    },
+    "flake-utils_2": {
+      "locked": {
+        "lastModified": 1653893745,
+        "narHash": "sha256-0jntwV3Z8//YwuOjzhV2sgJJPt+HY6KhU7VZUL0fKZQ=",
+        "owner": "numtide",
+        "repo": "flake-utils",
+        "rev": "1ed9fb1935d260de5fe1c2f7ee0ebaae17ed2fa1",
+        "type": "github"
+      },
+      "original": {
+        "owner": "numtide",
+        "repo": "flake-utils",
+        "type": "github"
+      }
+    },
+    "nixpkgs": {
+      "locked": {
+        "lastModified": 1655087213,
+        "narHash": "sha256-4R5oQ+OwGAAcXWYrxC4gFMTUSstGxaN8kN7e8hkum/8=",
+        "owner": "NixOS",
+        "repo": "nixpkgs",
+        "rev": "37b6b161e536fddca54424cf80662bce735bdd1e",
+        "type": "github"
+      },
+      "original": {
+        "owner": "NixOS",
+        "repo": "nixpkgs",
+        "rev": "37b6b161e536fddca54424cf80662bce735bdd1e",
+        "type": "github"
+      }
+    },
+    "nixpkgs_2": {
+      "locked": {
+        "lastModified": 1655046959,
+        "narHash": "sha256-gxqHZKq1ReLDe6ZMJSbmSZlLY95DsVq5o6jQihhzvmw=",
+        "owner": "NixOS",
+        "repo": "nixpkgs",
+        "rev": "07bf3d25ce1da3bee6703657e6a787a4c6cdcea9",
+        "type": "github"
+      },
+      "original": {
+        "owner": "NixOS",
+        "repo": "nixpkgs",
+        "type": "github"
+      }
+    },
+    "poetry2nix": {
+      "inputs": {
+        "flake-utils": "flake-utils_2",
+        "nixpkgs": "nixpkgs_2"
+      },
+      "locked": {
+        "lastModified": 1654921554,
+        "narHash": "sha256-hkfMdQAHSwLWlg0sBVvgrQdIiBP45U1/ktmFpY4g2Mo=",
+        "owner": "nix-community",
+        "repo": "poetry2nix",
+        "rev": "7b71679fa7df00e1678fc3f1d1d4f5f372341b63",
+        "type": "github"
+      },
+      "original": {
+        "owner": "nix-community",
+        "repo": "poetry2nix",
+        "rev": "7b71679fa7df00e1678fc3f1d1d4f5f372341b63",
+        "type": "github"
+      }
+    },
+    "root": {
+      "inputs": {
+        "flake-utils": "flake-utils",
+        "nixpkgs": "nixpkgs",
+        "poetry2nix": "poetry2nix"
+      }
+    }
+  },
+  "root": "root",
+  "version": 7
+}

flake.nix

@@ -0,0 +1,63 @@
+{
+  description = "Application packaged using poetry2nix";
+
+  inputs.flake-utils.url = "github:numtide/flake-utils?rev=0f8662f1319ad6abf89b3380dd2722369fc51ade";
+  inputs.nixpkgs.url = "github:NixOS/nixpkgs?rev=37b6b161e536fddca54424cf80662bce735bdd1e";
+  inputs.poetry2nix.url = "github:nix-community/poetry2nix?rev=7b71679fa7df00e1678fc3f1d1d4f5f372341b63";
+
+  outputs = { self, nixpkgs, flake-utils, poetry2nix }:
+    {
+      # Nixpkgs overlay providing the application
+      overlay = nixpkgs.lib.composeManyExtensions [
+        poetry2nix.overlay
+        (final: prev: {
+          # The application
+          deepdog = prev.poetry2nix.mkPoetryApplication {
+            overrides = final.poetry2nix.overrides.withDefaults (self: super: {
+              # …
+              # workaround https://github.com/nix-community/poetry2nix/issues/568
+              pdme = super.pdme.overridePythonAttrs (old: {
+                buildInputs = old.buildInputs or [ ] ++ [ final.python39.pkgs.poetry-core ];
+              });
+            });
+            projectDir = ./.;
+          };
+          deepdogEnv = prev.poetry2nix.mkPoetryEnv {
+            overrides = final.poetry2nix.overrides.withDefaults (self: super: {
+              # …
+              # workaround https://github.com/nix-community/poetry2nix/issues/568
+              pdme = super.pdme.overridePythonAttrs (old: {
+                buildInputs = old.buildInputs or [ ] ++ [ final.python39.pkgs.poetry-core ];
+              });
+            });
+            projectDir = ./.;
+          };
+        })
+      ];
+    } // (flake-utils.lib.eachDefaultSystem (system:
+      let
+        pkgs = import nixpkgs {
+          inherit system;
+          overlays = [ self.overlay ];
+        };
+      in
+      {
+        apps = {
+          deepdog = pkgs.deepdog;
+        };
+
+        defaultApp = pkgs.deepdog;
+        devShell = pkgs.mkShell {
+          buildInputs = [
+            pkgs.poetry
+            pkgs.deepdogEnv
+            pkgs.deepdog
+          ];
+          shellHook = ''
+            export DO_NIX_CUSTOM=1
+          '';
+          packages = [ pkgs.nodejs-16_x ];
+        };
+
+      }));
+}

jenkins/ci-agent-pod.yaml

@@ -1,9 +1,11 @@
 apiVersion: v1
 kind: Pod
 spec:
+  imagePullSecrets:
+    - name: regcreds
   containers:  # list of containers that you want present for your build, you can define a default container in the Jenkinsfile
-    - name: python
-      image: python:3.8
+    - name: poetry
+      image: ghcr.io/dmallubhotla/poetry-image:1
       command: ["tail", "-f", "/dev/null"]  # this or any command that is bascially a noop is required, this is so that you don't overwrite the entrypoint of the base container
       imagePullPolicy: Always # use cache or pull image for agent
       resources:  # limits the resources your build contaienr

pyproject.toml

@@ -1,18 +1,20 @@
 [tool.poetry]
 name = "deepdog"
-version = "0.6.1"
+version = "0.6.6"
 description = ""
 authors = ["Deepak Mallubhotla <dmallubhotla+github@gmail.com>"]
 
 [tool.poetry.dependencies]
 python = "^3.8,<3.10"
-pdme = "^0.8.3"
+pdme = "^0.8.6"
+numpy = "1.22.3"
+scipy = "1.10"
 
 [tool.poetry.dev-dependencies]
 pytest = ">=6"
 flake8 = "^4.0.1"
 pytest-cov = "^3.0.0"
-mypy = "^0.950"
+mypy = "^0.971"
 python-semantic-release = "^7.24.0"
 black = "^22.3.0"