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 and sepal width will be used
sepalLength = np.array(df['SepalLengthCm'])
sepalWidth = np.array(df['SepalWidthCm'])


    

In [4]:

    

# setting seaborn plot styles
sns.set()

# scatter plot
plt.plot(sepalLength, sepalWidth, marker='.', linestyle='none')
plt.xlabel('Sepal length [cm]')
plt.ylabel('Sepal width [cm]');


    

In [5]:

    

# the plot above is for all iris spieces, which can be listed via:
df['Species'].unique()


    

    
Out[5]:





array(['Iris-setosa', 'Iris-versicolor', 'Iris-virginica'], dtype=object)

In [6]:

    

# the remaining analysis will focus only on Iris-setosa
sepalLengthSetosa = np.array(df['SepalLengthCm'][df['Species'] == 'Iris-setosa'])
sepalWidthSetosa = np.array(df['SepalWidthCm'][df['Species'] == 'Iris-setosa'])

# scatter plot
plt.plot(sepalLengthSetosa, sepalWidthSetosa, marker='.', linestyle='none')
plt.xlabel('Sepal length [cm] Iris-setosa')
plt.ylabel('Sepal width [cm] Iris-setosa');


    

In [7]:

    

# linear regression
a, b = np.polyfit(sepalLengthSetosa, sepalWidthSetosa, 1)

# regression line
x = np.linspace(4, 6, 10)
y = a * x + b

# scatter plot with regression
plt.plot(sepalLengthSetosa, sepalWidthSetosa, marker='.', linestyle='none', label='data points')
plt.plot(x, y, color='green', label='lin reg line')
plt.legend(loc='lower right')
plt.xlabel('Sepal length [cm] Iris-setosa')
plt.ylabel('Sepal width [cm] Iris-setosa');


    

In [8]:

    

# second order regression
aa, bb, cc = np.polyfit(sepalLengthSetosa, sepalWidthSetosa, 2)

# regression line calculation
yy = aa * x**2 + bb * x + cc

# scatter plot with regression line
plt.plot(sepalLengthSetosa, sepalWidthSetosa, marker='.', linestyle='none', label='data points')
plt.plot(x, yy, color='red', label='quad reg line')
plt.legend(loc='lower right')
plt.xlabel('Sepal length [cm] Iris-setosa')
plt.ylabel('Sepal width [cm] Iris-setosa');


    

In [ ]: