import numpy as np

# code to get the data

#%load solutions/get-data-curl.py

#%load solutions/get-data-urllib.py

# code to load the data

#%load solutions/load-data.py

#look at the first few examples.
!cat data | grep "?"

# code to load the data without strings

%load solutions/load-data2.py

auto = np.genfromtxt("data", usecols=(0,1,2,3,4,5,6,7),
                     missing_values='?')


#missing values are displayed as nan. Let's take a look which columns have them
np.any(np.isnan(auto), axis=0)

# Now let's take a look which rows have them
np.any(np.isnan(auto), axis=1)

# code to remove nans
nan_rows = ? # fixme
auto = auto[:,:] # fixme

#%load solutions/remove-nans.py

import numpy.linalg as la

# code to fit and predict
def linreg(X,y):
    # 1. Add a column of 1's to X; now it has a total of p columns
    
    # 2. Calculate the weight vector w (should have p columns too)
    
    # 3. Calculate the predicted values of the target, y_pred
    
    # 4. Calculate the error, sse
    
    return w, y_pred, sse

# 1. Split the data into the training examples X (cylinders and displacement)
#    and target column y (miles per gallon)
X = auto[:,:] # fixme
y = auto[:,:] # fixme
print linreg(X,y)

#%load solutions/linreg.py

from math import sqrt

# code to print the RMS error

#%load solutions/rms.py

import matplotlib.pyplot as plt
%matplotlib inline

# predict and plot using just cylinders as a feature, print the sse
X = auto[:,:] # fixme
y = auto[:,:] # fixme
w, y_pred, sse = linreg(X, y)

plt.plot(X, y, 'o')
plt.plot(X, y_pred, 'r')
plt.show()

#%load solutions/predict-cylinders.py

# predict and plot using just weight as a feature, print the sse

#%load solutions/predict-and-plot.py