liliya2022

km = KMeans(n_clusters = 5)
y_predicted = km.fit_predict(salary_story[['Total Salary Paid', 'Home Price']])
salary_story['Cluster'] = y_predicted

liliya2022

from sklearn.cluster import KMeans
from sklearn.preprocessing import MinMaxScaler
from sklearn.preprocessing import LabelEncoder

liliya2022

sns.set(rc = {'figure.figsize':(14,7)})
sns.scatterplot(data = salary_story, x = 'Total Salary Paid',  y = 'Home Price').set(title = "Income per Home Price")

liliya2022

sns.set(rc = {'figure.figsize':(15,8)})
sns.distplot(a=salary_story['Total Salary Paid'], bins = 40, color='green',
             hist_kws={"edgecolor": 'black'}).set(title = "Density Plot for Income")
plt.show()

liliya2022

import scipy.stats as stats

plt.figure(figsize=(16, 10))

for f, label in ((same_1990s, "Not Remodelled"),
                 (remodelled_1990s, "Remodelled"),
                 (built_1990s, "Built after 1990")):
  x = np.sort(price[f])
  plt.hist(x, density=True, alpha=0.1)
  density = stats.gaussian_kde(x)

liliya2022

price = housing['SalePrice']
tot_liv_area = housing['TotLivArea']

plt.figure(figsize=(9, 6))
plt.scatter(tot_liv_area, price)
plt.ylabel('Sale Price')
plt.xlabel('TotLivArea')
plt.title('Sale Price per Total Living Area')
plt.show()

liliya2022

import seaborn as sns

sns.set(rc = {'figure.figsize':(15,8)})
sns.boxplot(x='OverallQual', y='SalePrice', data=housing).set(title = "House Overall Quality Boxplot")

liliya2022

#Import the following libraries
import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestRegressor
from sklearn.preprocessing import LabelEncoder
import matplotlib.pyplot as plt

#separate numerical and catergorical features
housing_numerical = housing.drop(['PID'], axis =1).select_dtypes(include = ('int64', 'float64'))

liliya2022

def get_feature_groups():
    num_features = housing.select_dtypes(include=['int64','float64']).columns
    return list(num_features.drop(['PID','SalePrice']))

num_features = get_feature_groups()

corr = housing[['SalePrice'] + num_features].corr()
corr = corr.sort_values('SalePrice', ascending=False)
plt.figure(figsize=(8,10))
sns.barplot(x=corr.SalePrice[1:], y=corr.index[1:], orient='h')

liliya2022

#libraries:
library(shiny)
library(shinythemes)
library(lubridate)
library(dygraphs)
library(xts)
library(tidyverse)


bitcoin <-read.csv(file = 'BTC-USD.csv', stringsAsFactors = F)