population-trend 5.9.0__py3-none-any.whl → 5.9.1__py3-none-any.whl

population_trend/__init__.py

@@ -1,10 +1,9 @@
 """A population growth model package"""
 
-__version__ = "5.9.0"
+__version__ = "5.9.1"
 from .calculate_growth_rates import *  # noqa
 from .cli import *  # noqa
 from .filter_data import *  # noqa
-from .plotter_growth_rate import *  # noqa
 from .plotter_population_trend_from_cpue import *  # noqa
 from .population_growth_model import *  # noqa
 from .regional_lambdas import *  # noqa

population_trend/calculate_growth_rates.py

@@ -1,11 +1,11 @@
 from bootstrapping_tools import (
     bootstrap_from_time_series,
-    calculate_intervals_from_p_values_and_alpha,
     calculate_p_values,
-    generate_latex_interval_string,
     get_bootstrap_deltas,
     lambda_calculator,
     power_law,
+    AbstractSeriesBootstrapper,
+    Bootstrap_from_time_series_parametrizer,
 )
 from matplotlib.ticker import MaxNLocator
 
@@ -67,27 +67,6 @@ def calculate_percent_diff_in_seasons(cantidad_nidos, model):
     return porcentaje_cambio
 
 
-class Bootstrap_from_time_series_parametrizer:
-    def __init__(self, blocks_length=3, N=2000, column_name="Maxima_cantidad_nidos", alpha=0.05):
-        self.parameters = dict(
-            dataframe=None,
-            column_name=column_name,
-            N=N,
-            return_distribution=True,
-            blocks_length=blocks_length,
-            alpha=alpha,
-        )
-
-    def set_data(self, data):
-        self.parameters["dataframe"] = data
-
-
-Bootstrap = dict(
-    default=Bootstrap_from_time_series_parametrizer(),
-    testing=Bootstrap_from_time_series_parametrizer(blocks_length=2, N=100),
-)
-
-
 def fit_population_model(seasons_series, data_series):
     parameters = lambda_calculator(seasons_series, data_series)
     model = power_law(
@@ -98,35 +77,19 @@ def fit_population_model(seasons_series, data_series):
     return model
 
 
-class Bootstrap_from_time_series:
+class LambdasBootstrapper(AbstractSeriesBootstrapper):
     def __init__(self, bootstrap_parametrizer):
-        self.parameters = bootstrap_parametrizer.parameters
-        self.lambdas_n0_distribution, _ = self._calculate_distribution_and_interval()
-        self.season_series = self.parameters["dataframe"]["Temporada"]
-        self.data_series = self.parameters["dataframe"][self.parameters["column_name"]]
-        self.lambdas = [lambdas_n0[0] for lambdas_n0 in self.lambdas_n0_distribution]
-        self.p_values = self.get_p_values()
-        self.intervals = self.intervals_from_p_values_and_alpha()
-        self.interval_lambdas = [interval[0] for interval in self.intervals]
-        self.lambda_latex_interval = self.get_lambda_interval_latex_string()
-
-    def intervals_from_p_values_and_alpha(self):
-        intervals = calculate_intervals_from_p_values_and_alpha(
-            self.lambdas_n0_distribution, self.p_values, self.parameters["alpha"]
-        )
-        return intervals
+        self.bootstrap_config = bootstrap_parametrizer.parameters
+        self.data_series = self.bootstrap_config["dataframe"][self.bootstrap_config["column_name"]]
+        self.season_series = self.bootstrap_config["dataframe"]["Temporada"]
+        self.parameters_distribution, _ = self.get_parameters_distribution()
 
-    def get_p_values(self):
-        p_value_mayor, p_value_menor = calculate_p_values(self.lambdas)
-        p_values = (p_value_mayor, p_value_menor)
-        return p_values
+    def get_parameters_distribution(self):
+        lambdas_n0_distribution, intervals = bootstrap_from_time_series(**self.bootstrap_config)
+        return lambdas_n0_distribution, intervals
 
     def get_distribution(self):
-        return self.lambdas_n0_distribution
-
-    def _calculate_distribution_and_interval(self):
-        lambdas_n0_distribution, intervals = bootstrap_from_time_series(**self.parameters)
-        return lambdas_n0_distribution, intervals
+        return self.parameters_distribution
 
     def get_inferior_central_and_superior_limit(self):
         inferior_limit, central, superior_limit = get_bootstrap_deltas(
@@ -134,11 +97,9 @@ class Bootstrap_from_time_series:
         )
         return inferior_limit, central, superior_limit
 
-    def get_lambda_interval_latex_string(self):
-        lambda_latex_string = generate_latex_interval_string(
-            self.interval_lambdas, deltas=False, **{"decimals": 2}
-        )
-        return lambda_latex_string
+    def fit_population_model(self):
+        model = fit_population_model(self.season_series, self.data_series)
+        return model
 
     def generate_season_interval(self):
         return "({}-{})".format(
@@ -154,34 +115,19 @@ class Bootstrap_from_time_series:
             seasons_intervals = calculate_seasons_intervals(monitored_seasons)
             return ",".join(seasons_intervals)
 
-    def fit_population_model(self):
-        model = fit_population_model(self.season_series, self.data_series)
-        return model
-
-    def get_intermediate_lambdas(self):
-        return [
-            lambda_n0
-            for lambda_n0 in self.lambdas_n0_distribution
-            if (lambda_n0[0] > self.intervals[0][0]) and (lambda_n0[0] < self.intervals[2][0])
-        ]
-
     def save_intervals(self, output_path):
-        json_dict = {
-            "intervals": list(self.intervals),
-            "lambda_latex_interval": self.lambda_latex_interval,
-            "p-values": self.p_values,
-            "bootstrap_intermediate_distribution": self.get_intermediate_lambdas(),
-        }
+        json_dict = self.get_parameters_dictionary()
+        json_dict["lambda_latex_interval"] = json_dict.pop("main_parameter_latex_interval")
         with open(output_path, "w") as file:
             json.dump(json_dict, file)
 
 
 def calculate_growth_rates_table(bootstrap: Bootstrap_from_time_series_parametrizer):
-    bootstraper = Bootstrap_from_time_series(bootstrap)
+    bootstraper = LambdasBootstrapper(bootstrap)
     df = bootstrap.parameters["dataframe"]
     model = bootstraper.fit_population_model()
     inferior_limit, central, superior_limit = bootstraper.get_inferior_central_and_superior_limit()
-    lambda_latex_string = bootstraper.get_lambda_interval_latex_string()
+    lambda_latex_string = bootstraper.lambda_latex_interval
     bootstrap_distribution = bootstraper.get_distribution()
     lambdas_distribution = [interval[0] for interval in bootstrap_distribution]
     p_value_mayor, p_value_menor = calculate_p_values(lambdas_distribution)

population_trend/cli.py

@@ -7,15 +7,16 @@ from population_trend.plotter_population_trend_from_cpue import (
     Plotter_Population_Trend_Model_From_CPUE,
 )
 from population_trend.calculate_growth_rates import (
-    Bootstrap_from_time_series_parametrizer,
-    Bootstrap_from_time_series,
+    LambdasBootstrapper,
 )
 from population_trend.regional_lambdas import (
     Island_Bootstrap_Distribution_Concatenator,
     Calculator_Regional_Lambdas_Intervals,
 )
 
-from population_trend.plotter_growth_rate import Plotter_Growth_Rate
+from population_trend.plotter_growth_rate import _Plotter_Growth_Rate
+from bootstrapping_tools import Bootstrap_from_time_series_parametrizer
+
 
 import pandas as pd
 from typing_extensions import Annotated
@@ -45,7 +46,7 @@ def write_bootstrap_intervals_json(
         alpha=alpha,
     )
     parametrizer.set_data(data)
-    bootstrap = Bootstrap_from_time_series(parametrizer)
+    bootstrap = LambdasBootstrapper(parametrizer)
     bootstrap.save_intervals(output_path)
 
 
@@ -130,7 +131,7 @@ def plot_growth_rate(
     lambdas_intervals_california = read_json(intervals_california)
     lambdas_intervals_pacific = read_json(intervals_pacific)
 
-    plotter = Plotter_Growth_Rate(lambdas_intervals_california, lambdas_intervals_pacific)
+    plotter = _Plotter_Growth_Rate(lambdas_intervals_california, lambdas_intervals_pacific)
     plotter.plot_error_bars()
     plt.savefig(output_path, transparent=True)
 

population_trend/plotter_growth_rate.py

@@ -2,7 +2,7 @@ import geci_plots as gp
 import matplotlib.pyplot as plt
 
 
-class Plotter_Growth_Rate:
+class _Plotter_Growth_Rate:
     def __init__(self, lambdas_dict, lambdas_dict_2):
         self.interval = [lambdas_dict["intervals"], lambdas_dict_2["intervals"]]
 

population_trend/regional_lambdas.py

@@ -1,9 +1,9 @@
 import numpy as np
 import json
 
-from bootstrapping_tools import calculate_intervals_from_p_values_and_alpha
+from bootstrapping_tools import calculate_intervals_from_p_values_and_alpha, calculate_p_values
 
-from population_trend.calculate_growth_rates import Bootstrap_from_time_series
+from population_trend.calculate_growth_rates import LambdasBootstrapper
 
 
 class Island_Bootstrap_Distribution_Concatenator:
@@ -54,24 +54,31 @@ class Island_Bootstrap_Distribution_Concatenator:
         return lambdas_distribution
 
 
-class Calculator_Regional_Lambdas_Intervals(Bootstrap_from_time_series):
+class Calculator_Regional_Lambdas_Intervals(LambdasBootstrapper):
     def __init__(self, regional_lambdas, alpha):
         self.lambdas = regional_lambdas
-        self.p_values = self.get_p_values()
         self.alpha = alpha
-        self.intervals = self.intervals_from_p_values_and_alpha()
-        self.interval_lambdas = [interval for interval in self.intervals]
-        self.lambda_latex_interval = self.get_lambda_interval_latex_string()
         self.hypothesis_test_statement_latex = self.get_hypotesis_statement()
         self.hypothesis_test_statement_latex_en = self.get_hypotesis_statement_en()
 
-    def intervals_from_p_values_and_alpha(self):
+    @property
+    def p_values(self):
+        p_value_mayor, p_value_menor = calculate_p_values(self.lambdas)
+        p_values = (p_value_mayor, p_value_menor)
+        return p_values
+
+    @property
+    def intervals(self):
         intervals = calculate_intervals_from_p_values_and_alpha(
             self.lambdas, self.p_values, self.alpha
         )
         return intervals
 
-    def get_intermediate_lambdas(self):
+    @property
+    def interval_lambdas(self):
+        return [interval for interval in self.intervals]
+
+    def get_lambdas_inside_confidence_interval(self):
         return [
             lambdas
             for lambdas in self.lambdas
@@ -106,7 +113,7 @@ class Calculator_Regional_Lambdas_Intervals(Bootstrap_from_time_series):
             "intervals": list(self.intervals),
             "lambda_latex_interval": self.lambda_latex_interval,
             "p-values": self.p_values,
-            "bootstrap_intermediate_distribution": self.get_intermediate_lambdas(),
+            "bootstrap_intermediate_distribution": self.get_lambdas_inside_confidence_interval(),
             "hypothesis_test_statement_latex_sp": self.hypothesis_test_statement_latex,
             "hypothesis_test_statement_latex_en": self.hypothesis_test_statement_latex_en,
         }

{population_trend-5.9.0.dist-info → population_trend-5.9.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: population_trend
-Version: 5.9.0
+Version: 5.9.1
 Summary: A population growth model package
 Home-page: https://github.com/IslasGECI/population_trend
 Author: Ciencia de Datos • GECI
@@ -8,7 +8,7 @@ Author-email: ciencia.datos@islas.org.mx
 Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 Classifier: License :: OSI Approved :: GNU General Public License v3 or later (GPLv3+)
-Requires-Dist: bootstrapping-tools==3.0.0
+Requires-Dist: bootstrapping-tools==3.*
 Requires-Dist: geci-plots
 Requires-Dist: typer[all]
 

population_trend-5.9.1.dist-info/RECORD

@@ -0,0 +1,13 @@
+population_trend/__init__.py,sha256=IKO9fZhfnavlCZgtkAkXVvIOV4zIie7auj4Ec9IjSNk,316
+population_trend/calculate_growth_rates.py,sha256=qD-a6O17CEhgKo0KmGzVGRpGuKpDQnno16MD3DgjVrk,6003
+population_trend/cli.py,sha256=wsAYBTBpegnvom_UCQqTyDgdE6OqraZ68EjcfXO3lJg,5435
+population_trend/filter_data.py,sha256=D0Y1vztcbbo98af9q7wRhlHfH__bNFI8tnVOdJY6hu0,403
+population_trend/plotter_growth_rate.py,sha256=jWMETGAahYNedyGJmxEzvjJdSNSPDsrpGlXrGIgDLQQ,1175
+population_trend/plotter_population_trend_from_cpue.py,sha256=US8h948Mtb9AQpDYfvt1c-35i2if9HxqcOp1q_R-rio,1351
+population_trend/population_growth_model.py,sha256=LWgMyEJqHY9M5Xuv9nVFSfX5_X61tXCBS2n-kvY8pNk,6002
+population_trend/regional_lambdas.py,sha256=5eCRXf9RWS0c6BG5F-Exico0GNMuUNyexZ0ZJKgOmp4,5274
+population_trend-5.9.1.dist-info/entry_points.txt,sha256=qVw9tnlMx7q2AnksVC2H4oK4ufQrdrbBzSODLH-bcac,61
+population_trend-5.9.1.dist-info/LICENSE,sha256=hIahDEOTzuHCU5J2nd07LWwkLW7Hko4UFO__ffsvB-8,34523
+population_trend-5.9.1.dist-info/WHEEL,sha256=EZbGkh7Ie4PoZfRQ8I0ZuP9VklN_TvcZ6DSE5Uar4z4,81
+population_trend-5.9.1.dist-info/METADATA,sha256=vs5I3SAYU6Kvv3PS8_otOxkwFKTCMiBJtm7WhDWA6u0,1330
+population_trend-5.9.1.dist-info/RECORD,,

population_trend-5.9.0.dist-info/RECORD

@@ -1,13 +0,0 @@
-population_trend/__init__.py,sha256=8PILFcMhthYOWPSs7LL974J3weCz9FMXRRVUCiea2vo,359
-population_trend/calculate_growth_rates.py,sha256=FzgAFt2NWc7jZW-v9qG8UCeqfMjyXzp_FT8b5mByNUw,7947
-population_trend/cli.py,sha256=KfIeLpr4uHHIeFMAfyjV_iKAdAVwXzVK4EglVQz8HcY,5419
-population_trend/filter_data.py,sha256=D0Y1vztcbbo98af9q7wRhlHfH__bNFI8tnVOdJY6hu0,403
-population_trend/plotter_growth_rate.py,sha256=4QWuCB_cKF4yWBzuNvtv1jadrT1GNstQ7cjgWXDL8ag,1174
-population_trend/plotter_population_trend_from_cpue.py,sha256=US8h948Mtb9AQpDYfvt1c-35i2if9HxqcOp1q_R-rio,1351
-population_trend/population_growth_model.py,sha256=LWgMyEJqHY9M5Xuv9nVFSfX5_X61tXCBS2n-kvY8pNk,6002
-population_trend/regional_lambdas.py,sha256=Hk1BWWqHjqf9zYarjt1Y7VNebeFmlX3xFpUFaMVdeoI,5222
-population_trend-5.9.0.dist-info/entry_points.txt,sha256=qVw9tnlMx7q2AnksVC2H4oK4ufQrdrbBzSODLH-bcac,61
-population_trend-5.9.0.dist-info/LICENSE,sha256=hIahDEOTzuHCU5J2nd07LWwkLW7Hko4UFO__ffsvB-8,34523
-population_trend-5.9.0.dist-info/WHEEL,sha256=EZbGkh7Ie4PoZfRQ8I0ZuP9VklN_TvcZ6DSE5Uar4z4,81
-population_trend-5.9.0.dist-info/METADATA,sha256=EnUbDSSifnPzSAF_PPJn33ZCqMVUsAkE_4Pwcnv59A8,1332
-population_trend-5.9.0.dist-info/RECORD,,