Numpy and Keras

Question 1

populate an array with a sequence of numbers:

Answer 1

sequence_of_integers = np.arange(5, 12)

Question 2

Matplotlib scatter plot

Answer 2

x = np.random.random([100])
y = np.random.random([100])
plt.scatter(x,y)

Question 3

Populate arrays with 20 random integer from 0 to 100

Answer 3

np.random.randint(low=0,high=101,size=20)

Question 4

Broadcasting

Answer 4

virtually expand the smaller operand to dimensions compatible

Question 5

Multiply each cell in a vector by 3

Answer 5

x*3

Question 6

Assign a sequence of integers from 6 to 20 (inclusive) to a NumPy array named feature.
Assign 15 values to a NumPy array named label such that:
label = (3)(feature) + 4

Answer 6

features = np.arange(6,21)
labels = (3*feature) + 4
plt.scatter(features,labels)

Question 7

Make a Dataframe from an array of array of data and and a list of column names.

Answer 7

my_dataframe = pd.DataFrame(data=my_data, columns=my_column_names)

Question 8

Create a new column named adjusted derived from the activity column.

Answer 8

my_dataframe[“adjusted”] = my_dataframe[“activity”] + 2

Question 9

Create an 3x4 (3 rows x 4 columns) pandas DataFrame in which the columns are named Eleanor, Chidi, Tahani, and Jason. Populate each of the 12 cells in the DataFrame with a random integer between 0 and 100, inclusive.

Answer 9

cn = [‘Eleanor’, ‘Chidi’, ‘Tahani’, ‘Jason’]
my_data = []
for i in range(3):
my_data.append(np.random.randint(0,101,4))

Question 10

Copying a DataFrame

Answer 10

pd.DataFrame.copy
Referencing. If you assign a DataFrame to a new variable, any change to the DataFrame or to the new variable will be reflected in the other.
Copying. If you call the pd.DataFrame.copy method, you create a true independent copy.

Question 11

Typical hyperparameters

Answer 11

learning rate
epochs
batch_size

Question 12

hyperparameter

Answer 12

The “knobs” that you tweak during successive runs of training a model. For example, learning rate is a hyperparameter.

Question 13

linear model

Answer 13

A model that assigns one weight per feature to make predictions. (Linear models also incorporate a bias.) By contrast, the relationship of weights to features in deep models is not one-to-one.

A linear model uses the following formula:

y_prime= b+ sigma(w_i,x_i)

Question 14

epoch

Answer 14

A full training pass over the entire dataset such that each example has been seen once.

Question 15

Relationship between epoch, batch_size and training iterations

Answer 15

epoch == N/batch_size

An epoch represents N/batch size training iterations, where N is the total number of examples.

Question 16

batch size

Answer 16

The system recalculates the model’s loss value and adjusts the model’s weights and bias after each iteration. Each iteration is the span in which the system processes one batch. For example, if the batch size is 6, then the system recalculates the model’s loss value and adjusts the model’s weights and bias after processing every 6 examples.

Question 17

An oscillating loss curve strongly suggests

Answer 17

learning rate is too high

Question 18

SGD Batch size

Answer 18

1
The batch size of a mini-batch is usually between 10 and 1000. Batch size is usually fixed during training and inference.

Question 19

TensorFlow does/does not permit dynamic batch sizes.

Answer 19

TensorFlow does permit dynamic batch sizes.

Question 20

Hyperparameter tuning

Answer 20

Training loss should steadily decrease, steeply at first, and then slowly until the slope of the loss curve approaches 0.
If the training loss does not converge, train for more epochs.
Training loss decreases too slowly: increase learning rate.
Training loss jumps around: decrease learning rate.
First, try large batch size values. Then, decrease the batch size until you see degradation.
Very large number of examples: reduce batch size to enable a batch to fit into memory.

Question 21

ideal combination of hyperparameters is

Answer 21

ideal combination of hyperparameters is data dependent: always experiment

Question 22

Pivot a table in pandas

Answer 22

data[“hours_since_admitted_rounded”] = round(data[“hours_since_admitted”])
pivoted = data.pivot_table(columns=”component_name”,values=”z_score_ord_num_value”, index=”hours_since_admitted_rounded”, fill_value=0)
pivoted.head(10)