maria-aguilera

import numpy as np

def standardize(gamma, upper_val = 0.3, lower_val = 0.1):

    s = (gamma-np.min(gamma))/(np.max(gamma)-np.min(gamma))
    out = s * (upper_val - lower_val) + lower_val

    return out

def is_pos_def(x):

maria-aguilera

"""
python3

numpy>=1.12.0
pandas>=0.19.2
matplotlib>=2.0.0
sklearn>=0.18
xgboost>=0.6
sortedcontainers>=1.5.7
"""

maria-aguilera

def categorical_summarized(dataframe, x=None, y=None, hue=None, palette='Set1', verbose=True):
    '''
    Helper function that gives a quick summary of a given column of categorical data

    Arguments
    =========
    dataframe: pandas dataframe
    x: str. horizontal axis to plot the labels of categorical data, y would be the count
    y: str. vertical axis to plot the labels of categorical data, x would be the count
    hue: str. if you want to compare it another variable (usually the target variable)

maria-aguilera

import seaborn as sns
import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inline

#adjust seaborn plot size
plt.figure(figsize=(20,12))

#pairplot (my favorite) - Draw scatterplots for joint relationships and histograms for univariate distributions
#hue optional like on all other seaborn plots

maria-aguilera

def plot_categorical_variables_pie(data, column_name, plot_defaulter = True, hole = 0):
    '''
    Function to plot categorical variables Pie Plots
    
    Inputs:
        data: DataFrame
            The DataFrame from which to plot
        column_name: str
            Column's name whose distribution is to be plotted
        plot_defaulter: bool

maria-aguilera

import seaborn as sns
from sklearn import preprocessing, ensemble
from scipy.stats import kendalltau
import pandas as pd
import random

#todo change module name
from tqdm import tqdm
import numpy as np
import pandas as pd

maria-aguilera

def plot_categorical(df: pd.DataFrame , col:str):
    """
    Function to plot the categorical data on piechart using Plotly
    @Args:
      df: pandas data frame
      col: A string column name within pandas data frame to plot
      
    Return:
      No object return, only visualization
    """

maria-aguilera

import altair as alt

#Simple Altait plot
import altair as alt
def plotGenericLineChart(x_values, x_type , y_values, y_type, chart_title, x_axis_title, y_axis_title):
    """
        This function creates a line chart for two values X and Y passed in along with thier types and titles
    """
    df = pd.DataFrame({"x_values" : x_values, 'y_values': y_values})
    chart = alt.Chart(df).mark_line(

maria-aguilera

# Function to print digits on top of Barplot
def show_values(axs, orient="v", space=.01):
    def _single(ax):
        if orient == "v":
            for p in ax.patches:
                _x = p.get_x() + p.get_width() / 2
                _y = p.get_y() + p.get_height() + (p.get_height()*0.01)
                value = '{:.2f}'.format(p.get_height())
                ax.text(_x, _y, value, ha="center") 
        elif orient == "h":