dsnd-probability-daivyd 0.2__tar.gz

dsnd_probability_daivyd-0.2/PKG-INFO

@@ -0,0 +1,4 @@
+Metadata-Version: 2.1
+Name: dsnd_probability_daivyd
+Version: 0.2
+Summary: Gaussian and Binomial distributions

dsnd_probability_daivyd-0.2/README.md

@@ -0,0 +1,7 @@
+#dsnd-probability-daivyd
+A python package for Gaussian and Binomial distributions.
+##Usage
+   from dsnd_probability_daivyd import Gaussian, Binomial
+   g = Gaussian(25, 2)
+   print(g)
+EOF

dsnd_probability_daivyd-0.2/dsnd_probability_daivyd/Binomialdistribution.py

@@ -0,0 +1,97 @@
+import math
+import matplotlib.pyplot as plt
+from .Generaldistribution import Distribution
+
+
+class Binomial(Distribution):
+    """Binomial distribution class for calculating and
+    visualizing a Binomial distribution.
+
+    Attributes:
+        mean (float) representing the mean value of the distribution
+        stdev (float) representing the standard deviation of the distribution
+        data_list (list of floats) a list of floats to be extracted from the data file
+        p (float) representing the probability of an event occurring
+        n (int) the total number of trials
+
+    """
+
+    def __init__(self, prob=0.5, size=20):
+        self.p = prob
+        self.n = size
+
+        Distribution.__init__(self, self.calculate_mean(), self.calculate_stdev())
+
+    def calculate_mean(self):
+        """Function to calculate the mean from p and n"""
+        self.mean = self.p * self.n
+        return self.mean
+
+    def calculate_stdev(self):
+        """Function to calculate the standard deviation from p and n."""
+        self.stdev = math.sqrt(self.n * self.p * (1 - self.p))
+        return self.stdev
+
+    def replace_stats_with_data(self):
+        """Function to calculate p and n from the data set"""
+        self.n = len(self.data)
+        self.p = sum(self.data) / self.n
+        self.mean = self.calculate_mean()
+        self.stdev = self.calculate_stdev()
+
+        return self.p, self.n
+
+    def plot_bar(self):
+        """Function to output a histogram of the instance variable data."""
+        plt.bar(x=['0', '1'], height=[
+            self.data.count(0), self.data.count(1)
+        ])
+        plt.title('Bar Chart of Data')
+        plt.xlabel('outcome')
+        plt.ylabel('count')
+
+    def pdf(self, k):
+        """Probability density function calculator for the binomial distribution."""
+        a = math.factorial(self.n) / (math.factorial(k) * (math.factorial(self.n - k)))
+        b = (self.p ** k) * (1 - self.p) ** (self.n - k)
+
+        return a * b
+
+    def plot_bar_pdf(self):
+        """Function to plot the pdf of the binomial distribution"""
+        x = []
+        y = []
+
+        for i in range(self.n + 1):
+            x.append(i)
+            y.append(self.pdf(i))
+
+        plt.bar(x, y)
+        plt.title('Distribution of Outcomes')
+        plt.ylabel('Probability')
+        plt.xlabel('Outcome')
+
+        plt.show()
+
+        return x, y
+
+    def __add__(self, other):
+        """Function to add together two Binomial distributions with equal p"""
+        try:
+            assert self.p == other.p, "p values are not equal"
+        except AssertionError as error:
+            raise
+
+        result = Binomial()
+        result.n = self.n + other.n
+        result.p = self.p
+        result.mean = result.calculate_mean()
+        result.stdev = result.calculate_stdev()
+
+        return result
+
+    def __repr__(self):
+        """Function to output the characteristics of the Binomial instance"""
+        return "mean {}, standard deviation {}, p {}, n {}".format(
+            self.mean, self.stdev, self.p, self.n
+        )

dsnd_probability_daivyd-0.2/dsnd_probability_daivyd/Gaussiandistribution.py

@@ -0,0 +1,173 @@
+import math
+import matplotlib.pyplot as plt
+from .Generaldistribution import Distribution
+
+
+class Gaussian(Distribution):
+    """Gaussian distribution class for calculating and
+    visualizing a Gaussian distribution.
+
+    Attributes:
+        mean (float) representing the mean value of the distribution
+        stdev (float) representing the standard deviation of the distribution
+        data_list (list of floats) a list of floats extracted from the data file
+
+    """
+
+    def __init__(self, mu=0, sigma=1):
+
+        Distribution.__init__(self, mu, sigma)
+
+    def calculate_mean(self):
+        """Function to calculate the mean of the data set.
+
+        Args:
+            None
+
+        Returns:
+            float: mean of the data set
+
+        """
+
+        avg = 1.0 * sum(self.data) / len(self.data)
+
+        self.mean = avg
+
+        return self.mean
+
+    def calculate_stdev(self, sample=True):
+        """Function to calculate the standard deviation of the data set.
+
+        Args:
+            sample (bool): whether the data represents a sample or population
+
+        Returns:
+            float: standard deviation of the data set
+
+        """
+
+        if sample:
+            n = len(self.data) - 1
+        else:
+            n = len(self.data)
+
+        mean = self.calculate_mean()
+
+        sigma = 0
+
+        for d in self.data:
+            sigma += (d - mean) ** 2
+
+        sigma = math.sqrt(sigma / n)
+
+        self.stdev = sigma
+
+        return self.stdev
+
+    def plot_histogram(self):
+        """Function to output a histogram of the instance variable data using
+        matplotlib pyplot library.
+
+        Args:
+            None
+
+        Returns:
+            None
+
+        """
+        plt.hist(self.data)
+        plt.title("Histogram of Data")
+        plt.xlabel("data")
+        plt.ylabel("count")
+
+    def pdf(self, x):
+        """Probability density function calculator for the gaussian distribution.
+
+        Args:
+            x (float): point for calculating the probability density function
+
+
+        Returns:
+            float: probability density function output
+        """
+
+        return (1.0 / (self.stdev * math.sqrt(2 * math.pi))) * math.exp(
+            -0.5 * ((x - self.mean) / self.stdev) ** 2
+        )
+
+    def plot_histogram_pdf(self, n_spaces=50):
+        """Function to plot the normalized histogram of the data and a plot of the
+        probability density function along the same range
+
+        Args:
+            n_spaces (int): number of data points
+
+        Returns:
+            list: x values for the pdf plot
+            list: y values for the pdf plot
+
+        """
+
+        mu = self.mean
+        sigma = self.stdev
+
+        min_range = min(self.data)
+        max_range = max(self.data)
+
+        # calculates the interval between x values
+        interval = 1.0 * (max_range - min_range) / n_spaces
+
+        x = []
+        y = []
+
+        # calculate the x values to visualize
+        for i in range(n_spaces):
+            tmp = min_range + interval * i
+            x.append(tmp)
+            y.append(self.pdf(tmp))
+
+        # make the plots
+        fig, axes = plt.subplots(2, sharex=True)
+        fig.subplots_adjust(hspace=0.5)
+        axes[0].hist(self.data, density=True)
+        axes[0].set_title("Normed Histogram of Data")
+        axes[0].set_ylabel("Density")
+
+        axes[1].plot(x, y)
+        axes[1].set_title(
+            "Normal Distribution for \n Sample Mean and Sample Standard Deviation"
+        )
+        axes[0].set_ylabel("Density")
+        plt.show()
+
+        return x, y
+
+    def __add__(self, other):
+        """Function to add together two Gaussian distributions
+
+        Args:
+            other (Gaussian): Gaussian instance
+
+        Returns:
+            Gaussian: Gaussian distribution
+
+        """
+
+        result = Gaussian()
+        result.mean = self.mean + other.mean
+        result.stdev = math.sqrt(self.stdev**2 + other.stdev**2)
+
+        return result
+
+    def __repr__(self):
+        """Function to output the characteristics of the Gaussian instance
+
+        Args:
+            None
+
+        Returns:
+            string: characteristics of the Gaussian
+
+        """
+
+        return "mean {}, standard deviation {}".format(self.mean, self.stdev)

dsnd_probability_daivyd-0.2/dsnd_probability_daivyd/Generaldistribution.py

@@ -0,0 +1,37 @@
+class Distribution:
+
+    def __init__(self, mu=0, sigma=1):
+        """Generic distribution class for calculating and
+        visualizing a probability distribution.
+
+        Attributes:
+            mean (float) representing the mean value of the distribution
+            stdev (float) representing the standard deviation of the distribution
+            data_list (list of floats) a list of floats extracted from the data file
+        """
+
+        self.mean = mu
+        self.stdev = sigma
+        self.data = []
+
+    def read_data_file(self, file_name):
+        """Function to read in data from a txt file. The txt file should have
+        one number (float) per line. The numbers are stored in the data attribute.
+
+        Args:
+            file_name (string): name of a file to read from
+
+        Returns:
+            None
+
+        """
+
+        with open(file_name) as file:
+            data_list = []
+            line = file.readline()
+            while line:
+                data_list.append(int(line))
+                line = file.readline()
+        file.close()
+
+        self.data = data_list

dsnd_probability_daivyd-0.2/dsnd_probability_daivyd/__init__.py

@@ -0,0 +1,4 @@
+from .Gaussiandistribution import Gaussian
+
+# TODO: import the Binomial class from the Binomialdistribution module
+from .Binomialdistribution import Binomial

dsnd_probability_daivyd-0.2/dsnd_probability_daivyd.egg-info/PKG-INFO

@@ -0,0 +1,4 @@
+Metadata-Version: 2.1
+Name: dsnd-probability-daivyd
+Version: 0.2
+Summary: Gaussian and Binomial distributions

dsnd_probability_daivyd-0.2/dsnd_probability_daivyd.egg-info/SOURCES.txt

@@ -0,0 +1,12 @@
+README.md
+setup.cfg
+setup.py
+dsnd_probability_daivyd/Binomialdistribution.py
+dsnd_probability_daivyd/Gaussiandistribution.py
+dsnd_probability_daivyd/Generaldistribution.py
+dsnd_probability_daivyd/__init__.py
+dsnd_probability_daivyd.egg-info/PKG-INFO
+dsnd_probability_daivyd.egg-info/SOURCES.txt
+dsnd_probability_daivyd.egg-info/dependency_links.txt
+dsnd_probability_daivyd.egg-info/not-zip-safe
+dsnd_probability_daivyd.egg-info/top_level.txt

dsnd_probability_daivyd-0.2/dsnd_probability_daivyd.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

dsnd_probability_daivyd-0.2/dsnd_probability_daivyd.egg-info/not-zip-safe

@@ -0,0 +1 @@
+

dsnd_probability_daivyd-0.2/dsnd_probability_daivyd.egg-info/top_level.txt

@@ -0,0 +1 @@
+dsnd_probability_daivyd

dsnd_probability_daivyd-0.2/setup.cfg

@@ -0,0 +1,7 @@
+[metadata]
+decription-file = README.md
+
+[egg_info]
+tag_build = 
+tag_date = 0
+

dsnd_probability_daivyd-0.2/setup.py

@@ -0,0 +1,9 @@
+from setuptools import setup
+
+setup(
+    name="dsnd_probability_daivyd",
+    version="0.2",
+    description="Gaussian and Binomial distributions",
+    packages=["dsnd_probability_daivyd"],
+    zip_safe=False,
+)