Month: December 2023

Posted on

FRIDAYY – DECEMBER 9,2023.

The python code :
# Convert dates to datetime objects
data[‘issued_date’] = pd.to_datetime(data[‘issued_date’], errors=’coerce’)
data[‘expiration_date’] = pd.to_datetime(data[‘expiration_date’], errors=’coerce’)
data[‘duration’] = (data[‘expiration_date’] – data[‘issued_date’]).dt.days
# Visualization 2: Number of permits issued over time (by year)
data[‘issued_year’] = data[‘issued_date’].dt.year
plt.figure(figsize=(10, 6))
sns.countplot(data=data, x=’issued_year’)
plt.title(‘Number of Permits Issued Over Time (by Year)’)
plt.xlabel(‘Year’)
plt.ylabel(‘Number of Permits’)
plt.xticks(rotation=45)
plt.tight_layout()
plt.show()
Posted on

WEDNESDAY – DECEMBER 6,2023.

After reviewing all datasets in the Analyze Boston, We have found a lot of null values and missing values in the different datasets. My teammates and I  have finalized the ” MOVING TRUCK PERMITS” dataset.

The basic python  code is

import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error, r2_score
from sklearn.preprocessing import LabelEncoder
from scipy.stats import chi2_contingency
import statsmodels.api as sm
from pandas.plotting import autocorrelation_plot
Posted on

MONDAY – DECEMBER 4, 2023.

  1. Different types of crimes in different areas:
  • Group the data by street and analyze the number of individual crime types on each street.
  • Visualize the results using bar charts or other suitable graphs.
  1. Most common types of crime, time of day, and day on certain streets:
  • Filter the data for each street and analyze the most common crime types, days, and hours.
  • Use bar charts, pie charts, or heat maps for visualization.
  1. The number of certain crimes in certain places:
  • Conduct a temporal analysis to identify trends in specific crime types over time.
  • Use line charts or other time series.
  1. Over time, the number of common crimes increases:
  • Analyze the general trend of common crimes across the dataset.
  • Consider creating a time series chart to visualize changes.
  1. General residential areas with crime:
  • Group the data by neighborhoods to identify areas with higher crime rates.
  • Visualize the results with maps or bar graphs.

 

  1. Time analysis:
  • Analyze data based on temporal factors such as month, day of the week, and time.
  • Identify patterns and trends over time with appropriate visualizations.

 

  1. Map Display:
  • Use the latitude and longitude data to draw the map.
  • Color-code or size-code data points based on the frequency of crime in each location.
  1. Correlation analysis:
  • Use statistical methods to identify relationships between different variables (eg, time of day, day, month) and types of crime.
  • Visualize correlations using correlation matrices or scatter plots.
  1. Analysis of shooting data:
  • Analyze shot data separately, and identify patterns and correlations with other variables.
  • Visualize image events on a map and examine temporal patterns.
  1. Forecasting models:
  • Depending on the nature of the data set, you can build predictive models to predict future crimes or classify incidents into different categories.
  • Common algorithms are decision trees, random forests or neural networks.
Posted on

FRIDAY – DECEMBER 1, 2023.

Geospatial Analysis of Violations

Geospatial examination of the dataset can provide valuable information about the geographic distribution of health disorders in different locations. Using the latitude and longitude data available for each facility, a map can be created that visually shows the concentration of violations in specific geographic areas. The purpose of this analysis is to find clusters of non-compliant facilities or areas with consistently high or low levels of compliance. In addition, adding demographic or economic information to the map can reveal relationships between the socioeconomic context of an area and compliance with the health and safety standards of food businesses. Geospatial tools and visualizations such as heat maps or choropleth maps can be used to comprehensively describe the spatial distribution of violations.