vaibkumr

import arrow

date=arrow.now().format('YYYY-MM-DD')
print(x)

vaibkumr

body{
  background-color: #262626;
}
h3,h2{
  font-family: 'Lato', sans-serif;
  font-weight: 300;
  color: pink;
}
hr{
  border-top: 1px dashed #8c8b8b;

vaibkumr

sudo telinit 0

vaibkumr

class RandomForest():
    def __init__(self, x, y, n_trees, sample_sz, min_leaf=5, depth = 10):
        np.random.seed(42)
        self.x, self.y, self.sample_sz, self.min_leaf, self.depth = x, y, sample_sz, min_leaf, depth
        self.trees = [self.create_tree() for i in range(n_trees)]

    def create_tree(self):
        rnd_idxs = np.random.permutation(len(self.y))[:self.sample_sz] #bagging
        return DecisionTree(self.x.iloc[rnd_idxs], self.y[rnd_idxs], min_leaf=self.min_leaf, depth = 10)
        

vaibkumr

class DecisionTree():
    def __init__(self, x, y, idxs=None, min_leaf=5, depth = 10):
        if idxs is None: idxs=np.arange(len(y)) #bagging with all the rows 
        self.x, self.y, self.idxs, self.min_leaf, self.depth = x, y, idxs, min_leaf, depth
        self.n, self.c = len(idxs), x.shape[1]
        self.val = np.mean(y[idxs])
        self.score = float('inf')
        self.find_varsplit()
        
    # This just does one decision; we'll make it recursive later

vaibkumr

class DecisionTree():
    def __init__(self, x, y, idxs=None, min_leaf=5, depth = 10):
        if idxs is None: idxs=np.arange(len(y)) #bagging with all the rows 
        self.x, self.y, self.idxs, self.min_leaf, self.depth = x, y, idxs, min_leaf, depth
        self.n, self.c = len(idxs), x.shape[1]
        self.val = np.mean(y[idxs])
        self.score = float('inf')
        self.find_varsplit()
        
    # For simplicity it does a single split, make it recursive later

vaibkumr

class DecisionTree():
    def __init__(self, x, y, idxs=None, min_leaf=5, depth = 10):
        if idxs is None: idxs=np.arange(len(y)) #bagging with all the rows 
        self.x, self.y, self.idxs, self.min_leaf, self.depth = x, y, idxs, min_leaf, depth
        self.n, self.c = len(idxs), x.shape[1]
        self.val = np.mean(y[idxs])
        self.score = float('inf')
        self.find_varsplit()
        
    # For simplicity it does a single split, make it recursive later

vaibkumr

class RandomForest():
    def __init__(self, x, y, n_trees, n_features, sample_sz, depth=10, min_leaf=5):
        np.random.seed(12)
        if n_features == 'sqrt':
            self.n_features = int(np.sqrt(x.shape[1]))
        elif n_features == 'log2':
            self.n_features = int(np.log2(x.shape[1]))
        else:
            self.n_features = n_features
        print(self.n_features, "sha: ",x.shape[1])    

vaibkumr

class DecisionTree():
    def __init__(self, x, y, n_features, f_idxs,idxs,depth=10, min_leaf=5):
        self.x, self.y, self.idxs, self.min_leaf, self.f_idxs = x, y, idxs, min_leaf, f_idxs
        self.depth = depth
        self.n_features = n_features
        self.n, self.c = len(idxs), x.shape[1]
        self.val = np.mean(y[idxs])
        self.score = float('inf')
        self.find_varsplit()
        

vaibkumr

    def find_better_split(self, var_idx):
        x, y = self.x.values[self.idxs,var_idx], self.y[self.idxs]
        sort_idx = np.argsort(x)
        sort_y,sort_x = y[sort_idx], x[sort_idx]
        rhs_cnt,rhs_sum,rhs_sum2 = self.n, sort_y.sum(), (sort_y**2).sum()
        lhs_cnt,lhs_sum,lhs_sum2 = 0,0.,0.

        for i in range(0,self.n-self.min_leaf-1):
            xi,yi = sort_x[i],sort_y[i]
            lhs_cnt += 1; rhs_cnt -= 1