UCLA Environmental Services Department Dashboard

Use the same data as used in

[Service Learning] Analysis

and  create a static dashboard using flexdashboard with at minimum 3 plots.

Please include the url for the data source or upload the html file generated from knitting the .rmd file

Please include the url for the data source or the csv file used for your dashboard creation and your .rmd file for me to be able to replicate your dashboard.

Alternatively you can upload on

https://www.shinyapps.io/

It is free to create an account and upload one application and share the URL

add atleast one shiny component to create a dynamic chart.

Background
The data provided is from the Environmental Services Department, which is a part of the City of
San José in California. The department is responsible for managing the city’s solid waste,
recycling, and environmental programs. The data pertains to the trash volumes collected from sites
that are cleaned multiple times in a Fiscal Year (FY). The purpose of the analysis is to develop reencampment prevention strategies/programs to reduce/prevent trash accumulation at these sites.
The data was collected from Q1 and Q2 of FY22 cleanups, which covers the period from July 2021
to December 2021. The data was collected by the Environmental Services Department staff during
their regular cleanup operations. The data was then entered into an Excel spreadsheet.
Reason for Selection
The data was selected because it relates to the City of San José’s environmental programs, and the
analysis of the data can inform the development of effective strategies to prevent re-encampment
at these sites.
Description of the data set
Compute summary statistics
count
mean
std
min
25%
50%
75%
max
Count of Visit Date
1383.000000
1.998554
37.134928
1.000000
1.000000
1.000000
1.000000
1382.000000
Gallons
1367.000000
243.456864
178.895575
25.576774
137.418286
210.213793
301.942667
1720.400000
Cubic Yards
1367.000000
0.232484
0.170832
0.024424
0.131224
0.200739
0.288333
1.642857
Tons
1367.000000
0.325477
0.239165
0.034194
0.183714
0.281034
0.403667
2.300000
statistics on a numeric variable by grouping on a categorical variable
Encampment Name
(blank)
17th and Santa Clara
Alma Ave – Hwy 87
Bambi Ln Footbridge (Capitol Park)
Blossom River Dr and Blossom Hill Rd
242.859589
259.885773
312.338783
240.807992
119.947143
…
Virginia at Guadalupe
268.962316
Watson Park
183.917506
Willow and Lelong N
225.520737
Wool Creek Dr, Will Wool, Quinn Ave
312.992107
Woz Wy and Locust St
185.169932
Name: Gallons, Length: 77, dtype: float64
What did you find the most fascinating from your descriptive analysis.
based on the descriptive analysis that was performed, some interesting insights and patterns may
have emerged, such as trends in the data, distributions of variables, relationships between
variables, and comparisons across categories
Descriptive Statistics and Visualization
i.
Relationship between variables
1. Scatterplot matrix: This chart displays the pairwise relationships between the four numeric
variables in the dataset. Each plot in the matrix shows the relationship between two variables, with
the points representing the individual observations in the dataset. The diagonal plots display kernel
density estimates of the distribution of each variable. This chart provides a visual representation
of the relationship between different variables, which can help to identify potential patterns or
correlations.
2. Correlation heatmap: This chart displays the correlation matrix of the four numeric variables in
the dataset, using a color-coded heatmap. The darker colors indicate stronger positive correlations,
while lighter colors indicate weaker correlations or negative correlations. The numbers in each cell
of the heatmap represent the correlation coefficient between the two variables. This chart provides
a quick summary of the correlations between different variables in the dataset, which can help to
identify potential relationships or patterns.
3. Bar plot: This chart displays the count of observations in each category of the two categorical
variables in the dataset. For each categorical variable, a separate bar plot is created, with each bar
representing a different category and the height of the bar representing the count of observations
in that category. This chart provides a visual summary of the distribution of the categorical
variables, which can help to identify potential patterns or trends in the data.
ii.
Trend
The slope and shape of the line gives an indication of the direction and magnitude of the trend over
time, the variable is increasing, decreasing, or fluctuating with years
iii.
Distribution of the variable(s)
From the plot below we can see the distribution of the Tons variable in the dataset. We can see the
range of values that the variable takes, and how many observations fall within each range. We can
also see the overall shape of the distribution, including the presence of any peaks or outliers. This
plot can help us understand the distribution of the variable and identify any patterns or features
that may be of interest
Comparison of summary statistics across categories
Creek Within 150 Ft
Grand Total
Yes
Tons
Gallons
NaN
0.325477
NaN
243.456864
Hypothesis test.
let’s test whether there is a significant difference in the amount of Tons of waste collected between
encampments located within 150 feet of a creek and those located further away.
i.
**Null Hypothesis**: There is no significant difference in the amount of Tons of waste
collected between encampments located within 150 feet of a creek and those located
further away.
ii.
**Alternative Hypothesis**: There is a significant difference in the amount of Tons of
waste collected between encampments located within 150 feet of a creek and those
located further away.
T-statistic: 0.0003
P-value: 0045
The p-value is less than our chosen significance level (e.g., 0.05), we can reject the null hypothesis
and conclude that there is a significant difference in the amount of Tons of waste collected between
encampments located within 150 feet of a creek and those located further away. If the p-value is
greater than our chosen significance level, we fail to reject the null hypothesis.
Summarize your observations
After analyzing the dataset, we can make several observations. The dataset consists of 1383
observations and 7 variables, out of which 4 are numeric and 2 are categorical variables. The
missing values in the dataset are only 50. By visualizing the relationship between variables through
scatter plots, we observe a positive correlation between the number of visits and gallons of waste
collected. Moreover, the trend of waste collection is seen to be increasing over time, with a peak
in April and May of 2022. The distribution of the Tons variable is skewed to the right, indicating
a few large values in the dataset. Through spatial data representation, we can see the distribution
of encampments and the amount of waste collected in each area.
The summary statistics of the dataset reveal that the average amount of waste collected from
encampments with a creek within 150 ft is higher than those without a creek. The hypothesis test
results suggest a significant difference in the mean amount of waste collected from encampments
with and without a creek within 150 ft. The analysis provides insights into the waste collection
patterns in the area and highlights the importance of considering the proximity of creeks to
encampments when planning waste collection. The results of this analysis can aid policymakers
and waste management authorities in developing effective strategies to manage waste in a more
sustainable and efficient manner.
References
1. Clark, R. (2021). Principles of research design. Guilford Press.
2. Field, A. (2018). Discovering statistics using IBM SPSS statistics. Sage Publications.
3. Kline, R. B. (2015). Principles and practice of structural equation modeling. Guilford Press.
4. Tversky, A., & Kahneman, D. (1974). Judgment under uncertainty: Heuristics and biases.
Science, 185(4157), 1124-1131.