Mudança no título do eixo da CDF, e remoção do slider de p-value

.vscode/settings.json

@@ -29,7 +29,7 @@
     ],
     "cSpell.language": "en,pt-BR",
     "python.formatting.provider": "black",
-    "python.pythonPath": "C:\\Users\\Weverton Marques\\.virtualenvs\\statfit-Hn-hXqrA\\Scripts\\python.exe",
+    "python.pythonPath": "/usr/bin/python3.7",
     "python.linting.pylintEnabled": true,
     "python.linting.enabled": true,
     "autoDocstring.docstringFormat": "google"

.vscode/tags

@@ -1,44 +1,44 @@
-!_TAG_FILE_FORMAT	2	/extended format; --format=1 will not append ;" to lines/
-!_TAG_FILE_SORTED	1	/0=unsorted, 1=sorted, 2=foldcase/
-!_TAG_OUTPUT_MODE	u-ctags	/u-ctags or e-ctags/
-!_TAG_PROGRAM_AUTHOR	Universal Ctags Team	//
-!_TAG_PROGRAM_NAME	Universal Ctags	/Derived from Exuberant Ctags/
-!_TAG_PROGRAM_URL	https://ctags.io/	/official site/
-!_TAG_PROGRAM_VERSION	0.0.0	/94653669/
-DISTS	..\\main.py	/^DISTS = [$/;"	kind:variable	line:20
-DISTS	..\\main.py.2c553062089a15597e815da9d769e9ae.py	/^DISTS = [$/;"	kind:variable	line:20
-Dist	..\\stats.py	/^class Dist:$/;"	kind:class	line:5
-Figure	..\\bokeh_models.py	/^def Figure(title, axis_labels, **kw):$/;"	kind:function	line:14
-Plot	..\\plot.py	/^class Plot:$/;"	kind:class	line:31
-Table	..\\plot.py	/^class Table:$/;"	kind:class	line:132
-UploadButton	..\\bokeh_models.py	/^def UploadButton(label, callback, **kw):$/;"	kind:function	line:36
-__init__	..\\plot.py	/^    def __init__(self, dists):$/;"	kind:member	line:133
-__init__	..\\plot.py	/^    def __init__(self, dists):$/;"	kind:member	line:34
-__init__	..\\stats.py	/^    def __init__(self, name, scipy, params):$/;"	kind:member	line:6
-bokeh_models.py	..\\bokeh_models.py	1;"	kind:file	line:1
-chi_squared	..\\stats.py	/^def chi_squared(cdf_function, values, hist, edges):$/;"	kind:function	line:13
-colors	..\\bokeh_models.py	/^from bokeh.palettes import Category10_10 as colors  # pylint: disable=no-name-in-module$/;"	kind:unknown	line:9
-cumulative	..\\plot.py	/^def cumulative(hist, edges):$/;"	kind:function	line:11
-kolmogorov_smirnov	..\\stats.py	/^def kolmogorov_smirnov(cdf, x, y):$/;"	kind:function	line:20
-main.py	..\\main.py	1;"	kind:file	line:1
-main.py.2c553062089a15597e815da9d769e9ae.py	..\\main.py.2c553062089a15597e815da9d769e9ae.py	1;"	kind:file	line:1
-make_plot	..\\main.py	/^    def make_plot(attr, old, new):$/;"	kind:function	line:50
-make_plot	..\\main.py.2c553062089a15597e815da9d769e9ae.py	/^    def make_plot(attr, old, new):$/;"	kind:function	line:50
-modify_doc	..\\main.py	/^def modify_doc(doc):$/;"	kind:function	line:29
-modify_doc	..\\main.py.2c553062089a15597e815da9d769e9ae.py	/^def modify_doc(doc):$/;"	kind:function	line:29
-np	..\\main.py	/^import numpy as np$/;"	kind:namespace	line:8
-np	..\\main.py.2c553062089a15597e815da9d769e9ae.py	/^import numpy as np$/;"	kind:namespace	line:8
-np	..\\plot.py	/^import numpy as np$/;"	kind:namespace	line:3
-np	..\\stats.py	/^import numpy as np$/;"	kind:namespace	line:1
-plot.py	..\\plot.py	1;"	kind:file	line:1
-plt	..\\bokeh_models.py	/^import bokeh.plotting as plt$/;"	kind:namespace	line:5
-server	..\\main.py	/^server = Server({"\/": modify_doc})$/;"	kind:variable	line:69
-server	..\\main.py.2c553062089a15597e815da9d769e9ae.py	/^server = Server({"\/": modify_doc})$/;"	kind:variable	line:69
-slider_callback	..\\main.py	/^    def slider_callback(attr, old, new):$/;"	kind:function	line:36
-slider_callback	..\\main.py.2c553062089a15597e815da9d769e9ae.py	/^    def slider_callback(attr, old, new):$/;"	kind:function	line:36
-ss	..\\stats.py	/^import scipy.stats as ss$/;"	kind:namespace	line:2
-stats.py	..\\stats.py	1;"	kind:file	line:1
-update_data	..\\plot.py	/^    def update_data(self, values):$/;"	kind:member	line:100
-update_histogram	..\\plot.py	/^    def update_histogram(self, hist, edges):$/;"	kind:member	line:88
-upload_callback	..\\bokeh_models.py	/^    def upload_callback(attr, old, new):$/;"	kind:function	line:78
-weverton	..\\stats.py	/^def weverton(cdf, x, y):$/;"	kind:function	line:24
+!_TAG_FILE_FORMAT	2	/extended format; --format=1 will not append ;" to lines/
+!_TAG_FILE_SORTED	1	/0=unsorted, 1=sorted, 2=foldcase/
+!_TAG_OUTPUT_MODE	u-ctags	/u-ctags or e-ctags/
+!_TAG_PROGRAM_AUTHOR	Universal Ctags Team	//
+!_TAG_PROGRAM_NAME	Universal Ctags	/Derived from Exuberant Ctags/
+!_TAG_PROGRAM_URL	https://ctags.io/	/official site/
+!_TAG_PROGRAM_VERSION	0.0.0	/94653669/
+DISTS	..\\main.py	/^DISTS = [$/;"	kind:variable	line:20
+DISTS	..\\main.py.2c553062089a15597e815da9d769e9ae.py	/^DISTS = [$/;"	kind:variable	line:20
+Dist	..\\stats.py	/^class Dist:$/;"	kind:class	line:5
+Figure	..\\bokeh_models.py	/^def Figure(title, axis_labels, **kw):$/;"	kind:function	line:14
+Plot	..\\plot.py	/^class Plot:$/;"	kind:class	line:31
+Table	..\\plot.py	/^class Table:$/;"	kind:class	line:132
+UploadButton	..\\bokeh_models.py	/^def UploadButton(label, callback, **kw):$/;"	kind:function	line:36
+__init__	..\\plot.py	/^    def __init__(self, dists):$/;"	kind:member	line:133
+__init__	..\\plot.py	/^    def __init__(self, dists):$/;"	kind:member	line:34
+__init__	..\\stats.py	/^    def __init__(self, name, scipy, params):$/;"	kind:member	line:6
+bokeh_models.py	..\\bokeh_models.py	1;"	kind:file	line:1
+chi_squared	..\\stats.py	/^def chi_squared(cdf_function, values, hist, edges):$/;"	kind:function	line:13
+colors	..\\bokeh_models.py	/^from bokeh.palettes import Category10_10 as colors  # pylint: disable=no-name-in-module$/;"	kind:unknown	line:9
+cumulative	..\\plot.py	/^def cumulative(hist, edges):$/;"	kind:function	line:11
+kolmogorov_smirnov	..\\stats.py	/^def kolmogorov_smirnov(cdf, x, y):$/;"	kind:function	line:20
+main.py	..\\main.py	1;"	kind:file	line:1
+main.py.2c553062089a15597e815da9d769e9ae.py	..\\main.py.2c553062089a15597e815da9d769e9ae.py	1;"	kind:file	line:1
+make_plot	..\\main.py	/^    def make_plot(attr, old, new):$/;"	kind:function	line:50
+make_plot	..\\main.py.2c553062089a15597e815da9d769e9ae.py	/^    def make_plot(attr, old, new):$/;"	kind:function	line:50
+modify_doc	..\\main.py	/^def modify_doc(doc):$/;"	kind:function	line:29
+modify_doc	..\\main.py.2c553062089a15597e815da9d769e9ae.py	/^def modify_doc(doc):$/;"	kind:function	line:29
+np	..\\main.py	/^import numpy as np$/;"	kind:namespace	line:8
+np	..\\main.py.2c553062089a15597e815da9d769e9ae.py	/^import numpy as np$/;"	kind:namespace	line:8
+np	..\\plot.py	/^import numpy as np$/;"	kind:namespace	line:3
+np	..\\stats.py	/^import numpy as np$/;"	kind:namespace	line:1
+plot.py	..\\plot.py	1;"	kind:file	line:1
+plt	..\\bokeh_models.py	/^import bokeh.plotting as plt$/;"	kind:namespace	line:5
+server	..\\main.py	/^server = Server({"\/": modify_doc})$/;"	kind:variable	line:69
+server	..\\main.py.2c553062089a15597e815da9d769e9ae.py	/^server = Server({"\/": modify_doc})$/;"	kind:variable	line:69
+slider_callback	..\\main.py	/^    def slider_callback(attr, old, new):$/;"	kind:function	line:36
+slider_callback	..\\main.py.2c553062089a15597e815da9d769e9ae.py	/^    def slider_callback(attr, old, new):$/;"	kind:function	line:36
+ss	..\\stats.py	/^import scipy.stats as ss$/;"	kind:namespace	line:2
+stats.py	..\\stats.py	1;"	kind:file	line:1
+update_data	..\\plot.py	/^    def update_data(self, values):$/;"	kind:member	line:100
+update_histogram	..\\plot.py	/^    def update_histogram(self, hist, edges):$/;"	kind:member	line:88
+upload_callback	..\\bokeh_models.py	/^    def upload_callback(attr, old, new):$/;"	kind:function	line:78
+weverton	..\\stats.py	/^def weverton(cdf, x, y):$/;"	kind:function	line:24

Procfile

@@ -1 +1 @@
-web: bokeh serve --port=$PORT --allow-websocket-origin=statfitweb.herokuapp.com --address=0.0.0.0 --use-xheaders .
+web: bokeh serve --port=$PORT --allow-websocket-origin=statfitweb.herokuapp.com --address=0.0.0.0 --use-xheaders .

main.py

@@ -23,7 +23,7 @@ def create_plot():
     plot = Plot(DISTS)
     numbins_slider = Slider(title="Number of bins", value=10, start=5, end=15, step=1)
     div = Div(text="<h2>Goodness of fit tests (p-values)</h2>")
-    pvalue_slider = Slider(title="Min p-value (%)", value=5, start=1, end=10, step=1)
+    # pvalue_slider = Slider(title="Min p-value (%)", value=5, start=1, end=10, step=1)
     table = Table([dist.name for dist in DISTS])
 
     def numbins_slider_callback(attr, old, new):
@@ -36,7 +36,7 @@ def numbins_slider_callback(attr, old, new):
         wms = [weverton(dist.cdf, data["x"], data["y"]) for dist in DISTS]
         table.source.data.update(ks=ks, chi=chi, wms=wms)
 
-    def pvalue_slider_callback(attr, old, new):
+    # def pvalue_slider_callback(attr, old, new):
         pass
 
     def make_plot(attr, old, new):
@@ -49,8 +49,8 @@ def make_plot(attr, old, new):
 
     button = UploadButton("Open file ...", make_plot, button_type="success")
     numbins_slider.on_change("value", numbins_slider_callback)
-    pvalue_slider.on_change("value", pvalue_slider_callback)
-    controls = column(button, numbins_slider, div, pvalue_slider, table.table)
+    # pvalue_slider.on_change("value", pvalue_slider_callback)
+    controls = column(button, numbins_slider, div, table.table)
     return row(controls, plot.layout, sizing_mode="scale_height")
 
 

plot.py

@@ -33,7 +33,7 @@ def __init__(self, dists):
         )
         self.cdf_plot = Figure(
             "Cumulative Probability Density",
-            ("Values", "Relative frequency"),
+            ("Values", "Cumulative frequency"),
             y_range=Range1d(start=0.0, end=1.02),
         )
         self.cdf_plot.line(

stats.py

@@ -1,119 +1,119 @@
-import numpy as np
-import scipy.stats as ss
-
-
-class Dist:
-    """Classe que associada a uma dada distribuição disponível na scipy.stats
-
-    Args:
-        name (str): nome da distribuição.
-        scipy (scipy.stats.rvs): classe de scipy.stats associada com a distribuição.
-        params (dict): dicionário com chaves equivalentes aos parâmetros de ajuste da distribuição.
-    """
-
-    def __init__(self, name, scipy, params):
-        """Construtor."""
-        self.name = name
-        self.scipy = scipy
-        self.params = params
-        self.pdf = None
-        self.cdf = None
-
-    def fit(self, values):
-        """Ajusta a distribuição para os valores das observações.
-
-        Args:
-            values (numpy.array): valores das observações
-        """
-        param = self.scipy.fit(values)
-        for key, value in zip(self.params.keys(), param):
-            self.params[key] = value
-        self.pdf = self.scipy(**self.params).pdf
-        self.cdf = self.scipy(**self.params).cdf
-
-
-DISTS = [
-    Dist("Normal", ss.norm, dict(loc=None, scale=None)),
-    Dist("Log-Normal", ss.lognorm, dict(s=None, loc=None, scale=None)),
-    Dist("Weibull", ss.weibull_min, dict(c=None, loc=None, scale=None)),
-    Dist("Gamma", ss.gamma, dict(a=None, loc=None, scale=None)),
-    Dist("Logistic", ss.logistic, dict(loc=None, scale=None)),
-]
-
-
-def cumulative(hist, edges):
-    """Cria um gráfico CDF (escada) com base no histograma.
-
-    Args:
-        hist (numpy.array): frequências relativas do histograma.
-        edges (numpy.array): lista de valores que limitam as classes do histograma.
-
-    Returns:
-        list[float]: coordenadas do x dos pontos do gráfico.
-        list[float]: coordenadas do y dos pontos do gráfico.
-    """
-    x = [edges[i // 2] for i in range(2 * len(edges[:-1]))]
-    x.append(edges[-1])
-    cdf = np.cumsum(hist * (edges[1] - edges[0]))
-    y = [cdf[(i - 1) // 2] for i in range(2 * len(cdf))]
-    y[0] = 0
-    y.append(cdf[-1])
-    return x, y
-
-
-def chi_squared(values, cdf_function, num_bins):
-    """Calcula o valor do teste Chi quadrado para um dado número de intervalos.
-
-    Args:
-        values (numpy.array): valores observados.
-        cdf_function (callable): função que calcula a CDF para um dados pontos.
-        num_bins (int): número de intervalos do histograma.
-
-    Returns:
-        float: p-value
-    """
-    hist, edges = np.histogram(values, density=True, bins=num_bins)
-    observed = hist * (edges[1] - edges[0]) * len(values)
-    expected = (cdf_function(edges)[1:] - cdf_function(edges)[:-1]) * len(values)
-    results = ss.chisquare(observed, expected)
-    return results[1]
-
-
-def kolmogorov_smirnov(values, cdf_function):
-    """Calcula o valor do teste Kolmogorov-Smirnov para um dado número de intervalos.
-
-    Args:
-        values (numpy.array): valores observados.
-        cdf_function (callable): função que calcula a CDF para um dados pontos.
-
-    Returns:
-        float: p-value
-    """
-    return ss.kstest(values, cdf_function)[1]
-
-
-def weverton(cdf, x, y):
-    """Calcula o valor do teste Chi quadrado para um dado número de intervalos.
-
-    Args:
-        cdf_function (callable): função que calcula a CDF para um dados pontos.
-        values (numpy.array): valores observados.
-        num_bins (int): número de intervalos do histograma.
-
-    Returns:
-        float: valor do teste.
-    """
-    return np.sum((cdf(x) - y) ** 2)
-
-
-if __name__ == "__main__":
-    values = np.linspace(-15, 15, 9)
-    DISTS[0].fit(values)
-    cdf_function = DISTS[0].cdf
-
-    results = ss.kstest(values, cdf_function)
-    print(f"KS: {results[0]:.3g}; p-value = {results[1]:.5g}")
-
-    n_bins = np.random.randint(1, len(values))
-    results = chi_squared(values, cdf_function, n_bins)
-    print(f"Chi: {results[0]:.3g}; p-value = {results[1]:.5g} ({n_bins} bins)")
+import numpy as np
+import scipy.stats as ss
+
+
+class Dist:
+    """Classe que associada a uma dada distribuição disponível na scipy.stats
+
+    Args:
+        name (str): nome da distribuição.
+        scipy (scipy.stats.rvs): classe de scipy.stats associada com a distribuição.
+        params (dict): dicionário com chaves equivalentes aos parâmetros de ajuste da distribuição.
+    """
+
+    def __init__(self, name, scipy, params):
+        """Construtor."""
+        self.name = name
+        self.scipy = scipy
+        self.params = params
+        self.pdf = None
+        self.cdf = None
+
+    def fit(self, values):
+        """Ajusta a distribuição para os valores das observações.
+
+        Args:
+            values (numpy.array): valores das observações
+        """
+        param = self.scipy.fit(values)
+        for key, value in zip(self.params.keys(), param):
+            self.params[key] = value
+        self.pdf = self.scipy(**self.params).pdf
+        self.cdf = self.scipy(**self.params).cdf
+
+
+DISTS = [
+    Dist("Normal", ss.norm, dict(loc=None, scale=None)),
+    Dist("Log-Normal", ss.lognorm, dict(s=None, loc=None, scale=None)),
+    Dist("Weibull", ss.weibull_min, dict(c=None, loc=None, scale=None)),
+    Dist("Gamma", ss.gamma, dict(a=None, loc=None, scale=None)),
+    Dist("Logistic", ss.logistic, dict(loc=None, scale=None)),
+]
+
+
+def cumulative(hist, edges):
+    """Cria um gráfico CDF (escada) com base no histograma.
+
+    Args:
+        hist (numpy.array): frequências relativas do histograma.
+        edges (numpy.array): lista de valores que limitam as classes do histograma.
+
+    Returns:
+        list[float]: coordenadas do x dos pontos do gráfico.
+        list[float]: coordenadas do y dos pontos do gráfico.
+    """
+    x = [edges[i // 2] for i in range(2 * len(edges[:-1]))]
+    x.append(edges[-1])
+    cdf = np.cumsum(hist * (edges[1] - edges[0]))
+    y = [cdf[(i - 1) // 2] for i in range(2 * len(cdf))]
+    y[0] = 0
+    y.append(cdf[-1])
+    return x, y
+
+
+def chi_squared(values, cdf_function, num_bins):
+    """Calcula o valor do teste Chi quadrado para um dado número de intervalos.
+
+    Args:
+        values (numpy.array): valores observados.
+        cdf_function (callable): função que calcula a CDF para um dados pontos.
+        num_bins (int): número de intervalos do histograma.
+
+    Returns:
+        float: p-value
+    """
+    hist, edges = np.histogram(values, density=True, bins=num_bins)
+    observed = hist * (edges[1] - edges[0]) * len(values)
+    expected = (cdf_function(edges)[1:] - cdf_function(edges)[:-1]) * len(values)
+    results = ss.chisquare(observed, expected)
+    return results[1]
+
+
+def kolmogorov_smirnov(values, cdf_function):
+    """Calcula o valor do teste Kolmogorov-Smirnov para um dado número de intervalos.
+
+    Args:
+        values (numpy.array): valores observados.
+        cdf_function (callable): função que calcula a CDF para um dados pontos.
+
+    Returns:
+        float: p-value
+    """
+    return ss.kstest(values, cdf_function)[1]
+
+
+def weverton(cdf, x, y):
+    """Calcula o valor do teste Chi quadrado para um dado número de intervalos.
+
+    Args:
+        cdf_function (callable): função que calcula a CDF para um dados pontos.
+        values (numpy.array): valores observados.
+        num_bins (int): número de intervalos do histograma.
+
+    Returns:
+        float: valor do teste.
+    """
+    return np.sum((cdf(x) - y) ** 2)
+
+
+if __name__ == "__main__":
+    values = np.linspace(-15, 15, 9)
+    DISTS[0].fit(values)
+    cdf_function = DISTS[0].cdf
+
+    results = ss.kstest(values, cdf_function)
+    print(f"KS: {results[0]:.3g}; p-value = {results[1]:.5g}")
+
+    n_bins = np.random.randint(1, len(values))
+    results = chi_squared(values, cdf_function, n_bins)
+    print(f"Chi: {results[0]:.3g}; p-value = {results[1]:.5g} ({n_bins} bins)")