#!/usr/bin/env python
# coding: utf-8

# <a href="https://colab.research.google.com/github/cyrus723/my-first-binder/blob/main/regression2.ipynb" target="_parent"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/></a>

# ## Data Source: FactSet, searching for all public company PE ratio, deleting row with missing observations, Could be significant bias introduced during deletion
# 

# In[1]:


import numpy as np
import pandas as pd
from pylab import mpl, plt
import statsmodels.formula.api as smf
import statsmodels.api as sm
plt.style.use('seaborn')
mpl.rcParams['font.family'] = 'serif'
get_ipython().run_line_magic('matplotlib', 'inline')


# In[2]:


import os 
os.getcwd()


# In[10]:


data = pd.read_csv('https://raw.githubusercontent.com/cyrus723/my-first-binder/main/data/Factset_corp.csv', header=0)  
data


# In[11]:


data.info()


# In[ ]:





# In[ ]:





# In[12]:


count_nan = data.isnull().sum()
print(count_nan)


# In[13]:


data2 = data.dropna()
data2


# In[14]:


data2.info()
data2.shape


# In[15]:


count_nan = data2.isnull().sum()
print(count_nan)


# In[16]:


formula = 'PE ~ EV_EBITDA + DY + ROE + D_EBITDA + SalesGrowth + EV_Sales + IntCoverage'
results = smf.ols(formula, data2).fit()
print(results.summary())


# In[17]:


data2.corr()


# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]: