In [7]:
import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inline
from patsy import dmatrices
In [8]:
pickle_name = 'the-numbers/consolidated.pickle'
df_movie_data = pd.read_pickle(pickle_name)
df_movie_data.head()
Out[8]:
In [11]:
# Set y and random variable X
y, X = dmatrices('Total Box ~ Budget + Release Year', data=df_movie_data, return_type='dataframe')
In [ ]: