Continue work on project 3.

README.md

@@ -4,7 +4,8 @@ This is my solution to the ML4T course exercises. The main page for the course
 is [here](http://quantsoftware.gatech.edu/Machine_Learning_for_Trading_Course).
 The page contains a link to the
 [assignments](http://quantsoftware.gatech.edu/CS7646_Spring_2020#Projects:_73.25).
-There are eight projects in total.
+There are eight projects in total. The summer 2020 page is
+[here](http://lucylabs.gatech.edu/ml4t/summer2020/).
 
 To set up the environment I have installed the following packages on my Linux
 Manjaro based system.
@@ -15,18 +16,16 @@ sudo pacman -S python-pandas --asdeps python-pandas-datareader python-numexpr \
                python-numpy
 ```
 
-I am also using the wonderful
-[mplfinance](https://github.com/matplotlib/mplfinance). You can install
-mplfinance via pip and find the tutorial
+I am also using [mplfinance](https://github.com/matplotlib/mplfinance) to plot
+candlestick-charts. You can install mplfinance via pip and find the tutorial
 [here](https://github.com/matplotlib/mplfinance#tutorials).
 
 ```
 pip install mplfinance --user
 ```
 
-Use unzip with the `-n` flag to extract the archives for the different
-exercises. This makes sure that you do not override any of the existing files. I
-might add a makefile to automize this later.
+I have included the archived version of the exercise. To extract them run the
+following command. The `-n` flag makes unzip never overwrite existing files.
 
 ```
 unzip -n zips/*.zip -d ./

assess_learners/DTLearner.py

@@ -1,28 +1,51 @@
 import numpy as np
 
+
 class DTLearner(object):
 
+    LEAF = -1
+    NA = -1
+
     def __init__(self, leaf_size = 1, verbose = False):
-        pass # move along, these aren't the drones you're looking for
+        self.leaf_size = leaf_size
+        self.verbose = verbose
 
     def author(self):
         return 'felixm' # replace tb34 with your Georgia Tech username
 
-    def addEvidence(self, dataX, dataY):
+    def create_node(self, factor: int, split: int, left: int, right: int):
+        return np.array((factor, split, left, right))
+
+
+    def build_tree(self, xs, y):
+        assert(xs.shape[0] == y.shape[0])
+        assert(xs.shape[0] > 0) # If this is 0 something went wrong.
+
+        if xs.shape[0] == 1:
+            return  self.create_node(self.LEAF, y[0], self.NA, self.NA)
+
+        if np.all(y[0] == y):
+            return self.create_node(self.LEAV, y[0], self.NA, self.NA)
+
+        # XXX: continue here
+        y = np.array([y])
+        correlations = np.corrcoef(xs, y, rowvar=True)
+        print(f"{correlations=}")
+
+        return 0
+
+    def addEvidence(self, data_x, data_y):
         """
         @summary: Add training data to learner
         @param dataX: X values of data to add
         @param dataY: the Y training values
         """
+        if self.verbose:
+            print(data_x)
+            print(data_y)
+        self.tree = self.build_tree(data_x, data_y)
 
-        # slap on 1s column so linear regression finds a constant term
-        newdataX = np.ones([dataX.shape[0], dataX.shape[1]+1])
-        newdataX[:,0:dataX.shape[1]] = dataX
 
-        # build and save the model
-        self.model_coefs, residuals, rank, s = np.linalg.lstsq(newdataX,
-                                                               dataY,
-                                                               rcond=None)
 
     def query(self,points):
         """
@@ -30,7 +53,8 @@ class DTLearner(object):
         @param points: should be a numpy array with each row corresponding to a specific query.
         @returns the estimated values according to the saved model.
         """
-        return (self.model_coefs[:-1] * points).sum(axis = 1) + self.model_coefs[-1]
+        return
+        # return (self.model_coefs[:-1] * points).sum(axis = 1) + self.model_coefs[-1]
 
 if __name__=="__main__":
     print("the secret clue is 'zzyzx'")

assess_learners/testlearner.py

@@ -33,8 +33,14 @@ if __name__=="__main__":
         print("Usage: python testlearner.py <filename>")
         sys.exit(1)
     inf = open(sys.argv[1])
+    # data = np.array([list(map(float,s.strip().split(',')[1:]))
+                     # for s in inf.readlines()[1:]])
     data = np.array([list(map(float,s.strip().split(',')[1:]))
-                     for s in inf.readlines()[1:]])
+                     for s in inf.readlines()])
+
+    # XXX: Get rid of some rows and columns for easier development.
+    # XXX: Remove later for testing!
+    # data = data[:10,5:]
 
     # compute how much of the data is training and testing
     train_rows = int(0.6* data.shape[0])
@@ -46,15 +52,18 @@ if __name__=="__main__":
     testX = data[train_rows:,0:-1]
     testY = data[train_rows:,-1]
 
-    print(f"{testX.shape}")
-    print(f"{testY.shape}")
+    # print(f"{testX.shape}")
+    # print(f"{testY.shape}")
 
     # create a learner and train it
     # learner = lrl.LinRegLearner(verbose = True) # create a LinRegLearner
     learner = dtl.DTLearner(verbose = True) # create a LinRegLearner
-    learner.addEvidence(trainX, trainY) # train it
+    # learner.addEvidence(trainX, trainY) # train it #XXX split back into test and non-test
+    learner.addEvidence(data[:,0:-1], data[:,-1])
     print(learner.author())
 
+    sys.exit(0)
+
     # evaluate in sample
     predY = learner.query(trainX) # get the predictions
     rmse = math.sqrt(((trainY - predY) ** 2).sum()/trainY.shape[0])