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

# <a href="https://colab.research.google.com/github/cyrus723/my-first-binder/blob/main/regression_FactSet3.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 S&P500 company PE ratio, no theoretical justification regarding the model specification

# In[36]:


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[37]:


import os 
os.getcwd()


# In[38]:


data = pd.read_csv('https://raw.githubusercontent.com/cyrus723/my-first-binder/main/data/sp500.csv', header=0)  
data


# In[39]:


data.info()


# In[48]:


data['cr'].plot.hist()


# In[60]:


data2=data.loc[(data['pe'] < 200) & (data['gm'] < 10000)]
data2.plot.scatter(x='pe', y='gm')


# In[ ]:





# In[ ]:


data2=data.dropna(subset=['mv'],axis=0)


# In[ ]:





# In[ ]:


data2


# In[ ]:


data2.info()


# In[ ]:


data2.describe()


# In[ ]:


data2['log_mv'] = np.log(data2['mv'])


# In[ ]:





# In[ ]:





# In[ ]:


formula = 'pe ~ beta + roe + de + altman + log_mv + gm + gsales + pvol	+ cap_s	+ dy	+ cr	+ cur'
results = smf.ols(formula, data2).fit()
print(results.summary())


# In[ ]:





# In[ ]:


data2.corr()


# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]: