data_analysis_project/data_analysis at main · Sinchana586/data_analysis_project · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
import pandas as pd
import matplotlib.pyplot as plt

# ----------------------------------
# Load Dataset
# ----------------------------------

df = pd.read_csv("/workspaces/data_analysis_project/dataset/titanic.csv")

print("First 5 Rows")
print(df.head())

print("\nDataset Shape:")
print(df.shape)

print("\nColumn Information:")
print(df.info())

# ----------------------------------
# Data Cleaning
# ----------------------------------

# Remove duplicate rows
df.drop_duplicates(inplace=True)

# Handle missing values
df["Age"] = df["Age"].fillna(df["Age"].median())


# Drop Cabin column (many missing values)
if "Cabin" in df.columns:
    df.drop("Cabin", axis=1, inplace=True)

print("\nMissing Values After Cleaning")
print(df.isnull().sum())

# ----------------------------------
# Filtering
# ----------------------------------

survivors = df[df["Survived"] == 1]

print("\nNumber of Survivors:")
print(len(survivors))

# ----------------------------------
# Grouping
# ----------------------------------

survival_by_gender = df.groupby("Sex")["Survived"].mean()

print("\nSurvival Rate by Gender")
print(survival_by_gender)

survival_by_class = df.groupby("Pclass")["Survived"].mean()

print("\nSurvival Rate by Passenger Class")
print(survival_by_class)

# ----------------------------------
# Summary Statistics
# ----------------------------------

print("\nSummary Statistics")
print(df.describe())

# ----------------------------------
# Insights
# ----------------------------------

print("\nKey Insights")

highest_gender = survival_by_gender.idxmax()
highest_class = survival_by_class.idxmax()

print(f"Highest survival rate by gender: {highest_gender}")
print(f"Highest survival rate by class: Class {highest_class}")

# ----------------------------------
# Graph 1: Survival by Gender
# ----------------------------------

plt.figure(figsize=(6,4))
survival_by_gender.plot(kind="bar")
plt.title("Survival Rate by Gender")
plt.ylabel("Survival Rate")
plt.tight_layout()
plt.savefig("survival_by_gender.png")
plt.show()

# ----------------------------------
# Graph 2: Survival by Passenger Class
# ----------------------------------

plt.figure(figsize=(6,4))
survival_by_class.plot(kind="bar")
plt.title("Survival Rate by Passenger Class")
plt.ylabel("Survival Rate")
plt.tight_layout()
plt.savefig("survival_by_class.png")
plt.show()