
# This Python 3 environment comes with many helpful analytics libraries installed
# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python
# For example, here's several helpful packages to load

import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
import matplotlib.pyplot as plt
%matplotlib inline
from matplotlib import style
# Input data files are available in the read-only "../input/" directory
# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory

import os
for dirname, _, filenames in os.walk('/kaggle/input'):
    for filename in filenames:
        print(os.path.join(dirname, filename))

# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using "Save & Run All" 
# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session


Gun=pd.read_csv("D:/ML & AI EDU/Gun Incidents/all_incidents.csv")
Population=pd.read_csv("D:/ML & AI EDU/Gun Incidents/2019_Census_US_Population_Data_By_State_Lat_Long.csv")
Population_City=pd.read_csv("D:/ML & AI EDU/Gun Incidents/top100cities (3).csv")
Holiday=pd.read_csv("D:/ML & AI EDU/Gun Incidents/US Holiday Dates (2004-2021).csv")


#Gun incidents by State
State_info1 = Gun.state.value_counts().rename_axis('State').reset_index(name='NumberofIncident').sort_values(by=["NumberofIncident"],ascending=True)
State_info1.to_csv('State_info1.csv',index=False)


fig = plt.figure(figsize=(15,12))
plt.barh(State_info1.State,State_info1.NumberofIncident,color="red")
plt.ylabel("States")
plt.xlabel("Number of Incident")
plt.title("Gun Incidents in United States by States")
plt.show()


#Gun incidents by cities
City_info1 = Gun.city.value_counts().rename_axis('city').reset_index(name='NumberofIncident').sort_values(by=["NumberofIncident"],ascending=True)
City_info1.to_csv('City_info1.csv',index=False)
City_info1=City_info1.tail(50)


fig = plt.figure(figsize=(15,12))
plt.barh(City_info1.city,City_info1.NumberofIncident,color="red")
plt.ylabel("Cities")
plt.xlabel("Number of Incident")
plt.title("Gun Incidents in United States by Cities")
plt.show()


#The Number Of Gun Incident Per 10000 Inhabitant Per Year By State
State_Gun=State_info1.merge(Population,left_on="State",right_on="STATE",suffixes=('_left', '_right'))
State_Gun["IncidentPerInhabitant"]=State_Gun.NumberofIncident/State_Gun.POPESTIMATE2019*10000/8
State_Gun=State_Gun.sort_values(by=["IncidentPerInhabitant"],ascending=True)


fig = plt.figure(figsize=(15,12))
plt.barh(State_Gun.State,State_Gun.IncidentPerInhabitant,color="red")
plt.ylabel("State")
plt.xlabel("Gun Incident in 10000 Inhabitant Per Year")
plt.title("Gun Incident in 10000 Inhabitant Per Year")
plt.show()


#The Number Of Gun Incident Per 10000 Inhabitant Per Year By City
City_info1=City_info1.head(50).sort_values(by=["NumberofIncident"],ascending=False)
City_info1.at[8,"city"]='St. Louis'


Population_City
City_Gun=City_info1.merge(Population_City,left_on="city",right_on="city",suffixes=('_left', '_right'))
City_Gun["IncidentPerInhabitant"]=City_Gun.NumberofIncident/City_Gun.population_2020*10000/8
City_Gun=City_Gun.sort_values(by=["IncidentPerInhabitant"],ascending=True)


fig = plt.figure(figsize=(15,12))
plt.barh(City_Gun.city,City_Gun.IncidentPerInhabitant,color="red")
plt.ylabel("State")
plt.xlabel("Gun Incident in 10000 Inhabitant Per Year")
plt.title("Gun Incident in 10000 Inhabitant Per Year")
plt.show()


Gun['date'] = pd.DatetimeIndex(Gun['date'])
Gun['year'] = Gun.date.dt.year
GunYear=Gun.year.value_counts().rename_axis('Year').reset_index(name='NumberofIncident').sort_values(by=["Year"],ascending=True).drop([8, 9])


#The Number Of Gun Incident From 2014 to 2021
fig = plt.figure(figsize=(12,10))
plt.bar(GunYear.Year,GunYear.NumberofIncident,color="red")
plt.ylabel("Number of Gun Incidents")
plt.xlabel("Year")
plt.title("Number of Gun Incidents")
plt.show()


#Gun incidents in holidays
Holiday["date"] = pd.DatetimeIndex(Holiday['Date'])
Holiday_Gun=Gun.merge(Holiday,left_on="date",right_on="date",suffixes=('_left', '_right'))
Holiday_Gun1=Holiday_Gun.Holiday.value_counts().rename_axis('Holiday').reset_index(name='NumberofIncident').sort_values(by=["NumberofIncident"],ascending=True)


Holiday_Gun1


fig = plt.figure(figsize=(15,12))
plt.barh(Holiday_Gun1.Holiday,Holiday_Gun1.NumberofIncident,color="red")
plt.ylabel("Holiday")
plt.xlabel("NumberofIncident")
plt.title("Number of Incident in Holiday")
plt.show()


#Number of Incident group by day of week
Gun["DateofWeek"]= pd.to_datetime(Gun.date, format ="%Y-%m-%d").dt.day_name()
GunDateofWeek=Gun.DateofWeek.value_counts().rename_axis('DateofWeek').reset_index(name='NumberofIncident').sort_values(by=["NumberofIncident"],ascending=False)


fig = plt.figure(figsize=(12,12))
plt.bar(GunDateofWeek.DateofWeek,GunDateofWeek.NumberofIncident,color="red")
plt.ylabel("NumberofIncident")
plt.xlabel("Day of Week")
plt.title("Number of Incident in Weekday")
plt.show()

	Holiday	NumberofIncident
17	Thanksgiving Day	1038
16	Christmas Day	1041
15	Washington's Birthday	1042
14	Valentine’s Day	1044
13	Thanksgiving Eve	1081
12	Christmas Eve	1108
11	Veterans Day	1152
10	Martin Luther King, Jr. Day	1195
9	Columbus Day	1212
8	New Year’s Eve	1351
7	Western Easter	1365
6	Juneteenth	1382
5	Labor Day	1455
4	Memorial Day	1480
3	Eastern Easter	1491
2	4th of July	1955
1	New Year's Day	2061
0	Labor Day Weekend	2920

Exploratory Data Analysis¶

Summary¶