Baseline model and assessment - Uses 100 days rather than cumsum versus unadjusted popularity¶
In [20]:
import pandas as pd
import numpy as np
%matplotlib inline
import matplotlib.pyplot as plt
In [13]:
df = pd.read_feather('../data/basemodel.feather')
df.head()
Out[13]:
In [48]:
from sklearn.linear_model import LinearRegression
from sklearn.preprocessing import PolynomialFeatures
from sklearn.pipeline import make_pipeline
from sklearn.grid_search import GridSearchCV
from sklearn.metrics import r2_score
from sklearn.metrics import mean_squared_error
model = LinearRegression(fit_intercept = True)
x = df[['popularity']]
y = df[['log_all_streams']]
def PolynomialRegression(degree=2, **kwargs):
return make_pipeline(PolynomialFeatures(degree), LinearRegression(**kwargs))
param_grid = {'polynomialfeatures__degree': np.arange(3), 'linearregression__normalize': [True, False]}
grid = GridSearchCV(PolynomialRegression(), param_grid, cv = 5, error_score=mean_squared_error)
grid.fit(x,y)
Out[48]:
In [49]:
model = grid.best_estimator_
y_pred = model.predict(x)
plt.scatter(y_pred, y_pred - y)
plt.hlines(y = 0, xmin = 6, xmax = 10)
rmse = np.sqrt(np.sum((y_pred - y)**2))
print(f'RMSE: {rmse}')
print(f'Rsq: {r2_score(y,y_pred)}')
In [50]:
plt.scatter(x,y)
lim = plt.axis()
plt.scatter(x,y_pred, c = 'red')
Out[50]:
Next iteration¶
- Evaluate outlier at 0 popularity. It seems to skew the results. It looks like linear would be a good fit here actually
In [52]:
df.sort_values('popularity')
Out[52]: