WillKoehrsen

import pandas as pd
import numpy as np

# Pandas options
pd.options.display.max_columns = 30
pd.options.display.max_rows = 20

from IPython import get_ipython
ipython = get_ipython()

WillKoehrsen

from sklearn.ensemble import RandomForestClassifier

# Create the model with 100 trees
model = RandomForestClassifier(n_estimators=100, 
                               bootstrap = True,
                               max_features = 'sqrt')
# Fit on training data
model.fit(train, train_labels)

WillKoehrsen

# Observations from multiple trips
c = np.array([[3, 2, 1],
              [2, 3, 1],
              [3, 2, 1],
              [2, 3, 1]])

with pm.Model() as model:
    # Parameters are a dirichlet distribution
    parameters = pm.Dirichlet('parameters', a=alphas, shape=3)
    # Observed data is a multinomial distribution

WillKoehrsen

import pymc3 as pm

# Context for the model
with pm.Model() as normal_model:
    
    # The prior for the data likelihood is a Normal Distribution
    family = pm.glm.families.Normal()
    
    # Creating the model requires a formula and data (and optionally a family)
    pm.GLM.from_formula(formula, data = X_train, family = family)

WillKoehrsen

# Create the blank plot
p = figure(plot_height = 600, plot_width = 600, 
           title = 'Histogram of Arrival Delays',
          x_axis_label = 'Delay (min)]', 
           y_axis_label = 'Number of Flights')

# Add a quad glyph with source this time
p.quad(bottom=0, top='flights', left='left', right='right', source=src,
       fill_color='red', line_color='black', fill_alpha = 0.75,
       hover_fill_alpha = 1.0, hover_fill_color = 'navy')

WillKoehrsen

# Pandas for data management
import pandas as pd

# os methods for manipulating paths
from os.path import dirname, join

# Bokeh basics 
from bokeh.io import curdoc
from bokeh.models.widgets import Tabs

WillKoehrsen

with pm.Model() as sleep_model:
    
    # Create the alpha and beta parameters
    # Assume a normal distribution
    alpha = pm.Normal('alpha', mu=0.0, tau=0.05, testval=0.0)
    beta = pm.Normal('beta', mu=0.0, tau=0.05, testval=0.0)
    
    # The sleep probability is modeled as a logistic function
    p = pm.Deterministic('p', 1. / (1. + tt.exp(beta * time + alpha)))
    

WillKoehrsen

from keras.models import Sequential
from keras.layers import LSTM, Dense, Dropout, Masking, Embedding

model = Sequential()

# Embedding layer
model.add(
    Embedding(input_dim=num_words,
              input_length = training_length,
              output_dim=100,

WillKoehrsen

from sklearn.tree import DecisionTreeClassifier

# Make a decision tree and train
tree = DecisionTreeClassifier(random_state=RSEED)
tree.fit(X, y)

WillKoehrsen

import lightgbm as lgb

def identify_zero_importance_features(train, train_labels, iterations = 2):
    """
    Identify zero importance features in a training dataset based on the 
    feature importances from a gradient boosting model. 
    
    Parameters
    --------
    train : dataframe