Data Exploration
Four major insights through visualization:
Insight 1: Distribution of Complaint Types
1
Output:
Two visualisations are produced by this code to examine the distribution of complaint
types. To arrange the output, a header is printed first. It imports the required libraries,
including cm for colour management, seaborn for improved graphics, numpy for
numerical computations, and matplotlib for basic charting.
2
Insight 2: Average Request Closing Time by Complaint Type
Output:
3
Insight 3: Correlation Heatmap
Output:
4
Insight 4: Distribution of Request Closing Time
Output:
5
Insight Complaints are clustered in certain geographic areas, particularly in
residential neighbourhoods.
This could help in resource allocation for the NYPD.
6
Insight Complaints show seasonal variation with peaks in summer months
(June-August), likely due to more outdoor activities and open windows during
warmer weather.
7
Arrangement of the complaint types according to their average
'Request_Closing_Time', categorized by various locations . Illustrate it
through graph as well.
Code:
Output:
8
Statistical Testing
Test 1:
Code:
9
10
Output:
11
Test 2:
Code:
Output:
12
Report Structure
Referencing
13
