In [1]:

    

# standard libraries
import numpy as np
import pandas as pd

# for plotting
import matplotlib.pyplot as plt
import pickle

# for interpreting data
from pyechonest import artist

# for machine learning
from sklearn.ensemble import RandomForestRegressor as rf
from scipy.sparse import coo_matrix

from pyechonest import config
config.ECHO_NEST_API_KEY='EIVX1I4WCCD7FQRFV'

# turn off to avoid displaying test output
display = False


    

In [2]:

    

qfile = "adjusted_quantiles_thing.csv"


    

In [3]:

    

qdata = pd.read_csv(qfile)


    

In [10]:

    

%matplotlib
plt.hist(qdata[qdata.plays < 3500].plays, bins=40)
plt.title("Quantile Predictions truncated at 3500")
plt.xlabel("Number of Play Counts")
plt.ylabel("Play Counts")


    

    




Using matplotlib backend: TkAgg






    
Out[10]:





<matplotlib.text.Text at 0x1f3df668>

In [12]:

    

bfile = "kevs_rocks.csv"
bdata = pd.read_csv(bfile)


    

In [13]:

    

plt.hist(bdata[bdata.plays < 3500].plays, bins=40)
plt.title("Normal Prediction truncated at 3500")
plt.xlabel("Number of Play Counts")
plt.ylabel("Play Counts")


    

    
Out[13]:





<matplotlib.text.Text at 0x1f3df668>

In [14]:

    

plt.title("Quantile (blue) and Normal (green) Predictions")


    

    
Out[14]:





<matplotlib.text.Text at 0x1f5ca7b8>

In [16]:

    

f = plt.figure()
plt.hist(np.log(bdata[bdata.plays < 3500].plays), bins=40)
plt.title("Log of Normal Prediction truncated at 3500")
plt.xlabel("Number of Log Play Counts")
plt.ylabel("Log Play Counts")


    

    
Out[16]:





<matplotlib.text.Text at 0x1f9a3208>

In [ ]: