In [1]:

    

# importing required modules
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
%matplotlib inline
import numpy as np

# runing the functions script
%run stats_func.py


    

In [2]:

    

# loading the iris dataset
df = pd.read_csv('iris.csv')
df.head()


    

    
Out[2]:






  

    

      

      
Id
      
SepalLengthCm
      
SepalWidthCm
      
PetalLengthCm
      
PetalWidthCm
      
Species
    
  
  

    

      
0
      
1
      
5.1
      
3.5
      
1.4
      
0.2
      
Iris-setosa
    
    

      
1
      
2
      
4.9
      
3.0
      
1.4
      
0.2
      
Iris-setosa
    
    

      
2
      
3
      
4.7
      
3.2
      
1.3
      
0.2
      
Iris-setosa
    
    

      
3
      
4
      
4.6
      
3.1
      
1.5
      
0.2
      
Iris-setosa
    
    

      
4
      
5
      
5.0
      
3.6
      
1.4
      
0.2
      
Iris-setosa
    
  

In [3]:

    

# for further analysis Sepal Length variable will be used

# plotting the selected variable
sns.boxplot('SepalLengthCm', data=df);


    

In [4]:

    

sns.swarmplot('SepalLengthCm', data=df);


    

In [5]:

    

# converting Sepal Length to numpy array

sepalLength = df['SepalLengthCm']
type(sepalLength)


    

    
Out[5]:





pandas.core.series.Series

In [6]:

    

sepalLength = np.array(sepalLength)
type(sepalLength)


    

    
Out[6]:





numpy.ndarray

In [7]:

    

# use of Empirical Cumulative Density Function (ECDF)
x, y = ecdf(sepalLength)

# plot of the data
plt.plot(x, y, marker='.', linestyle='none')
plt.xlabel('Sepal Length [cm]')
plt.ylabel('ECDF');


    

In [8]:

    

# generating the normal distribution points with mean and std_dev derived from the dataset
mu = np.mean(sepalLength)
sigma = np.std(sepalLength)
sepalNormDistr = np.random.normal(mu, sigma, 10000)

# ECDF function
x_n, y_n = ecdf(sepalNormDistr)

# plotting all together
plt.plot(x, y, marker='.', linestyle='none', label='empirical')
plt.plot(x_n, y_n, color='red', label='norm distr')
plt.legend()
plt.xlabel('Sepal Length [cm]')
plt.ylabel('CDF');


    

In [9]:

    

# comparison with expotential distribution
sepalExpDistr = np.random.exponential(mu, 10000)

# ECDF function
x_e, y_e = ecdf(sepalExpDistr)

# plotting
plt.plot(x, y, marker='.', linestyle='none', label='empirical')
plt.plot(x_e, y_e, color='orange', label='exp distr')
plt.legend()
plt.xlabel('Sepal Length [cm]')
plt.ylabel('CDF');


    

In [10]:

    

# histogram
plt.hist(sepalLength, bins=30, edgecolor='black')
plt.xlabel('Sepal Length [cm]')
plt.ylabel('Frequency / count');


    

In [ ]: