Tahsin Mayeesha Tahsin-Mayeesha

Interactive Machine Learning

Taught by Brad Knox at the MIT Media Lab in 2014. Course website. Lecture and visiting speaker notes.

Power to the People: The Role of Humans in Interactive Machine Learning by Knox, Cakmak, Kulesza, Amershi, and Lau
A Few Useful Things to Know about Machine Learning by Domingos
Machine Learning that Matters by Wagstaff
Beyond Concise and Colorful: Learning Intelligible Rules by Pazzani et al.
[Designing Games with a Purpose] (https://www.cs.cmu.edu/~biglou/GWAP_CACM.pdf) by von Ahn and Dabbish
[Human Model Evaluation in Interactive Supervised

Tahsin Mayeesha is currently working with Berkman Klein Center Of Internet and Society on interactive network visualization project as a participant of Google Summer Of Code 2018. Previously, she worked in Cramstack on electricity data, a data science startup in Bangladesh focusing on consulting and government project. Currently she's an undergraduate student in North South University, Bangladesh majoring in computer science. She runs "Learning Machine Learning" publication in Medium featuring tutorials and projects. Mayeesha graduated from Udacity's Machine Learning Nanodegree in 2017 and also participated in Fast.ai as an international fellow.

	import pandas as pd
	datelist = pd.date_range(pd.datetime.today(), periods =365).date.tolist()
	f = open("2018_planner.txt","w")
	for date in datelist:
	f.write("# " + str(date) + '\n')
	f.close()

	# this has to be first to make sure that matplotlib runs in headless mode
	import matplotlib
	matplotlib.use("Agg")

	import sys
	import numpy as np
	import warnings
	warnings.filterwarnings('ignore')

	from fa2l import force_atlas2_layout

	def set_node_color(G,color_by,colormap=None):
	"""
	Returns a list of colors for each node based on the provided colormap.

	Parameters
	___________

	G : graph.
	A networkx graph.

	import math
	import networkx as nx
	from itertools import combinations
	from utils import set_node_size
	from fa2l import force_atlas2_layout


	def get_distance(pos1,pos2):
	""" Returns distance between two points

	---------------------------------------------------------------------------
	InvalidArgumentError Traceback (most recent call last)
	~\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py in get_attr(self, name)
	2325 with c_api_util.tf_buffer() as buf:
	-> 2326 c_api.TF_OperationGetAttrValueProto(self._c_op, name, buf)
	2327 data = c_api.TF_GetBuffer(buf)

	InvalidArgumentError: Operation 'StatefulPartitionedCall' has no attr named '_XlaCompile'.

	During handling of the above exception, another exception occurred:

	class LanguageClassifier(tf.train.Checkpoint):
	def __init__(self,language_module,num_labels,dense_units=(128,128),dropouts=(0.1,0.1)):

	# initialization stuff
	super(LanguageClassifier,self).__init__()
	self.language_module = language_module
	self.model_encoder = language_module.model


	# classifier head layers