Added other files

README.md

@@ -0,0 +1 @@
+# Traffic-Accident-Analysis

dt.r

@@ -0,0 +1,18 @@
+library(party)
+print(head(readingSkills))
+dataset<-read.csv("Data_Final.csv")
+
+high=ifelse(dataset$SEVERITY>=2,"MODERATE","HIGH")
+check=ifelse(dataset$SEVERITY>=2,"HIGH","MODERATE")
+
+dataset=data.frame(dataset,high)
+dataset=data.frame(dataset,check)
+
+input.dat <- dataset[c(1:10000),]
+png(file = "decision_tree_example9.png")
+
+#dataset = dataset[,-31]
+names(dataset)
+output.tree <- ctree(high ~ DAY_OF_WEEK + LIGHT_CONDITION, data = input.dat)
+plot(output.tree)
+dev.off()

severity.py

@@ -0,0 +1,36 @@
+# -*- coding: utf-8 -*-
+
+import numpy as np
+import matplotlib.pyplot as plt
+import pandas as pd
+import seaborn as sns
+# Importing the dataset
+dataset = pd.read_csv('Data_Final.csv')
+X = dataset.iloc[:,:].values
+X = np.delete(X,2,axis=1)
+X = np.delete(X,1,axis=1)
+X = np.delete(X,0,axis=1)
+names = (dataset.columns.values)
+names = names[3:]
+
+from sklearn.preprocessing import Imputer
+imputer = Imputer(missing_values='NaN',strategy="most_frequent",axis=0)
+imputer = imputer.fit(X[:,:])
+X[:,:] = imputer.transform(X[:,:])
+data_new = pd.DataFrame(data=X,columns=names)
+
+imputer = Imputer(missing_values=-1,strategy="most_frequent",axis=0)
+imputer = imputer.fit(X[:,:])
+X[:,:] = imputer.transform(X[:,:])
+data_new = pd.DataFrame(data=X,columns=names)
+
+
+
+plt.figure(figsize=(30,8))
+
+sns.countplot(x='LIGHT_CONDITION', hue='SEVERITY',data=data_new)
+sns.countplot(x='SEVERITY',hue='ALCOHOLTIME',data=data_new)
+sns.countplot(x='LIGHT_CONDITION',hue='ALCOHOLTIME',data=data_new)
+sns.countplot(x='SEVERITY',hue='SPEED_ZONE',data=data_new)
+sns.countplot(x='POLICE_ATTEND',hue='SPEED_ZONE',data=data_new)
+sns.countplot(x='FEMALES',hue='SEVERITY',data=data_new)

time_of_day_UK.py

@@ -0,0 +1,74 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Tue May 1 17:40:46 2018
+
+@author: Prashant
+"""
+
+import numpy as np
+import matplotlib.pyplot as plt
+import pandas as pd
+dataset = pd.read_csv("Accidents0515.csv")
+
+
+time1=dataset['Time']
+time=dataset['Time'].values
+
+t=[]
+j=0
+for i in time:
+ t.append((i))
+ j+=1
+x = []
+for i in range(len(t)):
+ s = t[i]
+ x.append(s[0:2])
+import math
+j=0
+for i in x:
+ x[j] = math.ceil(int(i)/3)
+ j+=1
+
+accident_time = {}
+for i in x:
+ if i in accident_time:
+ accident_time[i]+=1
+ else:
+ accident_time[i]=1
+accident_time[1]+=accident_time[0]
+del(accident_time[0])
+
+val=[]
+for i in sorted(accident_time):
+ val.append(accident_time[i])
+
+plt.figure(figsize=(10,5))
+label = ['12am-3am','3am-6am','6am-9am','9am-12pm','12pm-3pm','3pm-6pm','6pm-9pm','9pm-12am']
+plt.bar(list(accident_time.keys()),accident_time.values())
+plt.xticks([1,2,3,4,5,6,7,8],label)
+plt.xlabel('Time (3-hour period)')
+plt.ylabel('Total deaths')
+
+
+day_of_week = dataset['Day_of_Week'].values
+day_freq = {}
+for i in day_of_week:
+ if(math.isnan(i)):
+ pass
+ elif int(i) not in day_freq:
+ day_freq[int(i)]=1
+ else:
+ day_freq[int(i)]+=1
+
+labels = 'Monday', 'Tuesday', 'Wednesday', 'Thursday','Friday','Saturday','Sunday'
+sizes = [day_freq[1],day_freq[2],day_freq[3],day_freq[4],day_freq[5],day_freq[6],day_freq[7]]
+fig1, ax1 = plt.subplots()
+ax1.pie(sizes, labels=labels, autopct='%1.1f%%',
+ shadow=True, startangle=90)
+ax1.axis('equal') # Equal aspect ratio ensures that pie is drawn as a circle.
+
+plt.show()
+
+
+#for i in X:
+

time_of_day_india.py

@@ -0,0 +1,34 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Tue May 1 10:59:30 2018
+
+@author: Prashant
+"""
+
+import numpy as np
+import matplotlib.pyplot as plt
+import pandas as pd
+import seaborn as sns
+
+data = pd.read_csv('Traffic accidents by time of occurrence 2001-2014.csv')
+X = data.iloc[18,:].values
+
+accident_time = {1:X[3],2:X[4],3:X[5],4:X[6],5:X[7],6:X[8],7:X[9],8:X[10]}
+times = list(accident_time.keys())
+label = ['0-3Hrs','3-6Hrs','6-9Hrs','9-12Hrs','12-15Hrs','15-18Hrs','18-21Hrs','21-24Hrs']
+#no_of_accidents1 = [X[3],X[4],X[5],X[6],X[7],X[8],X[9],X[10]]
+#no_of_accidents = list(accident_time.values())
+plt.figure(figsize=(30,8))
+#plt.bar(times,no_of_accidents)
+
+
+val=[]
+for i in sorted(accident_time):
+ val.append(accident_time[i])
+
+plt.figure(figsize=(10,5))
+
+plt.bar(list(accident_time.keys()),accident_time.values())
+plt.xticks([1,2,3,4,5,6,7,8],label)
+plt.xlabel('Time (3-hour period)')
+plt.ylabel('Total deaths')