├── README.md
└── ca2.py


/README.md:
--------------------------------------------------------------------------------
1 | # Python-project


--------------------------------------------------------------------------------
/ca2.py:
--------------------------------------------------------------------------------
  1 | import pandas as pd
  2 | import numpy as np
  3 | import matplotlib.pyplot as plt
  4 | import seaborn as sns
  5 | df=pd.read_csv(r"C:\Users\91934\OneDrive\Desktop\Electric_Vehicle_Population_Data.csv")
  6 | print(df.isnull().sum())
  7 | df["County"]=df["County"].fillna(df["County"].mode()[0])
  8 | df["City"]=df["City"].fillna(df["City"].mode()[0])
  9 | df["Postal Code"]=df["Postal Code"].fillna(df["Postal Code"].median())
 10 | df["Legislative District"]=df["Legislative District"].fillna(df["Legislative District"].median())
 11 | df["Vehicle Location"]=df["Vehicle Location"].fillna(df["Vehicle Location"].mode()[0])
 12 | df["Electric Utility"]=df["Electric Utility"].fillna(df["Electric Utility"].mode()[0])
 13 | df["2020 Census Tract"]=df["2020 Census Tract"].fillna(df["2020 Census Tract"].mode()[0])
 14 | print(df.isnull().sum())
 15 | #1)Find out which electric vehicle types are common in top cities
 16 | 
 17 | # Count vehicle types per city
 18 | top_cities = df['City'].value_counts().head(10).index
 19 | filtered = df[df['City'].isin(top_cities)]
 20 | 
 21 | # Group by city and vehicle type
 22 | type_counts = filtered.groupby(['City', 'Electric Vehicle Type']).size().unstack()
 23 | type_counts.plot(kind='bar', figsize=(12,6))
 24 | plt.title("Electric Vehicle Types in Top Cities")
 25 | plt.xlabel("City")
 26 | plt.ylabel("Count")
 27 | plt.xticks(rotation=45)
 28 | plt.legend(title="Vehicle Type")
 29 | plt.tight_layout()
 30 | plt.show()
 31 | 
 32 | # 2. Check how electric range changes across different vehicle makes
 33 | 
 34 | plt.figure(figsize=(12,6))
 35 | sns.scatterplot(x="Make", y="Electric Range",data=df)
 36 | plt.title("Electric Range by Vehicle Make")
 37 | plt.xticks(rotation=90)
 38 | plt.tight_layout()
 39 | plt.show()
 40 | 
 41 | 
 42 | #3 Compare number of EVs by model year
 43 | model_year_counts = df['Model Year'].value_counts().sort_index()
 44 | 
 45 | plt.figure(figsize=(10,5))
 46 | plt.bar(model_year_counts.index.astype(str), model_year_counts.values, color='skyblue')
 47 | plt.xlabel("Model Year")
 48 | plt.ylabel("Number of EVs")
 49 | plt.title("EV Adoption by Model Year")
 50 | plt.xticks(rotation=45)
 51 | plt.tight_layout()
 52 | plt.show()
 53 | 
 54 | 
 55 | #4.Find the most popular vehicle in "make" and "model"
 56 | top_makes = df['Make'].value_counts().head(5)
 57 | 
 58 | plt.figure(figsize=(8,5))
 59 | plt.pie(top_makes.values, labels=top_makes.index, autopct='%1.1f%%', startangle=140)
 60 | plt.title("Top 5 EV Makes")
 61 | plt.show()
 62 | 
 63 | # Optional: Top models
 64 | top_models = df['Model'].value_counts().head(5)
 65 | plt.figure(figsize=(8,5))
 66 | plt.bar(top_models.index, top_models.values, color='green')
 67 | plt.title("Top 5 EV Models")
 68 | plt.xlabel("Model")
 69 | plt.ylabel("Count")
 70 | plt.xticks(rotation=30)
 71 | plt.tight_layout()
 72 | plt.show()
 73 | 
 74 | 
 75 | #5. Explore EV popularity by ZIP Code or City
 76 | 
 77 | 
 78 | zip_counts = df['Postal Code'].value_counts().head(10)
 79 | 
 80 | plt.figure(figsize=(10,6))
 81 | plt.bar(zip_counts.index.astype(str), zip_counts.values, color='orange')
 82 | plt.title("Top 10 ZIP Codes with Most EVs")
 83 | plt.xlabel("ZIP Code")
 84 | plt.ylabel("Number of EVs")
 85 | plt.xticks(rotation=45)
 86 | plt.tight_layout()
 87 | plt.show()
 88 | 
 89 | 
 90 | 
 91 | #6.Finding out which electric car make is used the most by using a bar graph
 92 | 
 93 | # Count the number of cars for each make
 94 | make_counts = df['Make'].value_counts().head(10)  # Top 10 makes
 95 | 
 96 | # Create bar graph
 97 | plt.figure(figsize=(10,5))
 98 | plt.bar(make_counts.index, make_counts.values, color='skyblue')
 99 | plt.title("Top 10 Most Used Electric Vehicle Makes")
100 | plt.xlabel("Make")
101 | plt.ylabel("Number of Vehicles")
102 | plt.xticks(rotation=45)
103 | plt.tight_layout()
104 | plt.show()
105 | 
106 | #7. This will show how many vehicles fall into different electric range values.
107 | 
108 | # Histogram of Electric Range
109 | plt.figure(figsize=(10,5))
110 | plt.hist(df['Electric Range'], bins=20, color='purple', edgecolor='black')
111 | plt.title("Distribution of Electric Range")
112 | plt.xlabel("Electric Range (miles)")
113 | plt.ylabel("Number of Vehicles")
114 | plt.grid()
115 | plt.tight_layout()
116 | plt.show()
117 | 
118 | 
119 | 
120 | 
121 | 
122 | #8.Heatmap: Correlation Between Numeric Columns
123 | #This will show relationships between numeric features like Electric Range, Model Year
124 | 
125 | 
126 | # Selecting numeric columns for correlation
127 | numeric_data = df[['Model Year', 'Electric Range']]
128 | 
129 | # Create the correlation matrix
130 | corr_matrix = numeric_data.corr()
131 | 
132 | # Plot heatmap
133 | plt.figure(figsize=(6,4))
134 | sns.heatmap(corr_matrix, annot=True, cmap="YlGnBu", linewidths=0.5)
135 | plt.title("Correlation Heatmap")
136 | plt.tight_layout()
137 | plt.show()
138 | 
139 | 
140 | 
141 | 
142 | 
143 | 
144 | 
145 | 
146 | 
147 | 
148 | 
149 | 
150 | 
151 | 
152 | 
153 | 
154 | 


--------------------------------------------------------------------------------