WillKoehrsen

from sklearn.datasets import load_iris
iris = load_iris()

# Model (can also use single decision tree)
from sklearn.ensemble import RandomForestClassifier
model = RandomForestClassifier(n_estimators=10)

# Train
model.fit(iris.data, iris.target)
# Extract single tree

WillKoehrsen

# Import the libraries
import matplotlib.pyplot as plt
import seaborn as sns

# matplotlib histogram
plt.hist(flights['arr_delay'], color = 'blue', edgecolor = 'black',
         bins = int(180/5))

# seaborn histogram
sns.distplot(flights['arr_delay'], hist=True, kde=False, 

WillKoehrsen

# selenium for web driving
import selenium
from selenium import webdriver

# time for pausing between navigation
import time

# Datetime for recording time of submission
import datetime

WillKoehrsen

# Show 4 different binwidths
for i, binwidth in enumerate([1, 5, 10, 15]):
    
    # Set up the plot
    ax = plt.subplot(2, 2, i + 1)
    
    # Draw the plot
    ax.hist(flights['arr_delay'], bins = int(180/binwidth),
             color = 'blue', edgecolor = 'black')
    

WillKoehrsen

# Examines the effect of changing a single variable
# Takes in the name of the variable, the trace, and the data
def model_effect(query_var, trace, X):
    
    # Variables that do not change
    steady_vars = list(X.columns)
    steady_vars.remove(query_var)
    
    # Linear Model that estimates a grade based on the value of the query variable 
    # and one sample from the trace

WillKoehrsen

 # Both inputs are 1-dimensional
book = Input(name = 'book', shape = [1])
link = Input(name = 'link', shape = [1])

# Embedding the book (shape will be (None, 1, 50))
book_embedding = Embedding(name = 'book_embedding',
                           input_dim = len(book_index),
                           output_dim = embedding_size)(book)

# Embedding the link (shape will be (None, 1, 50))

WillKoehrsen

# Threshold for removing correlated variables
threshold = 0.9

# Absolute value correlation matrix
corr_matrix = app.corr().abs()

# Upper triangle of correlations
upper = corr_matrix.where(np.triu(np.ones(corr_matrix.shape), k=1).astype(np.bool))

# Select columns with correlations above threshold

WillKoehrsen

import cufflinks as cf

@interact
def scatter_plot(x=list(df.select_dtypes('number').columns), 
                 y=list(df.select_dtypes('number').columns)[1:],
                 theme=list(cf.themes.THEMES.keys()), 
                 colorscale=list(cf.colors._scales_names.keys())):
    
    df.iplot(kind='scatter', x=x, y=y, mode='markers', 
             xTitle=x.title(), yTitle=y.title(), 

WillKoehrsen

from torchvision import datasets
from torch.utils.data import DataLoader

# Datasets from folders
data = {
    'train':
    datasets.ImageFolder(root=traindir, transform=image_transforms['train']),
    'valid':
    datasets.ImageFolder(root=validdir, transform=image_transforms['valid']),
}

WillKoehrsen

# Function to calculate correlation coefficient between two arrays
def corr(x, y, **kwargs):
    
    # Calculate the value
    coef = np.corrcoef(x, y)[0][1]
    # Make the label
    label = r'$\rho$ = ' + str(round(coef, 2))
    
    # Add the label to the plot
    ax = plt.gca()