├── README.md
└── Python_project
    ├── Python.ca2 (1).pdf
    └── pythonproject.txt


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


--------------------------------------------------------------------------------
/Python_project/Python.ca2 (1).pdf:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/rahulvarma9676/python-project/HEAD/Python_project/Python.ca2 (1).pdf


--------------------------------------------------------------------------------
/Python_project/pythonproject.txt:
--------------------------------------------------------------------------------
  1 | import pandas as pd
  2 | import numpy as np
  3 | import matplotlib.pyplot as plt
  4 | import seaborn as sns
  5 | from scipy.stats import zscore
  6 | 
  7 | # Load dataset
  8 | df = pd.read_csv("C:\\Users\\rahul\\Downloads\\serious-injury-outcome-indicators-2000-2023.csv")
  9 | 
 10 | # Info about the dataset
 11 | print("Dataset Info:")
 12 | print(df.info())
 13 | print("\nFirst 5 Rows:")
 14 | print(df.head())
 15 | 
 16 | # Check for missing values
 17 | print("\nMissing Values:\n", df.isnull().sum())
 18 | 
 19 | # -------------------------------
 20 | # Statistical Summary
 21 | numeric_cols = ['Data_value', 'Lower_CI', 'Upper_CI']
 22 | print("\nStatistical Summary:\n", df[numeric_cols].describe())
 23 | 
 24 | # -------------------------------
 25 | # Outlier Detection using Z-Score
 26 | z_scores = np.abs(zscore(df[numeric_cols]))
 27 | outliers = (z_scores > 3)
 28 | print("\nOutliers (Z-Score > 3):\n", outliers.sum())
 29 | 
 30 | # -------------------------------
 31 | # Correlation Heatmap
 32 | plt.figure(figsize=(8, 6))
 33 | sns.heatmap(df[numeric_cols].corr(), annot=True, cmap='coolwarm')
 34 | plt.title('Correlation Heatmap')
 35 | plt.show()
 36 | 
 37 | # -------------------------------
 38 | # Boxplot for Outliers
 39 | plt.figure(figsize=(8, 6))
 40 | sns.boxplot(data=df[numeric_cols])
 41 | plt.title('Boxplot - Outliers')
 42 | plt.show()
 43 | 
 44 | # -------------------------------
 45 | # Line Chart of Data over Time
 46 | df['Period'] = pd.to_datetime(df['Period'], errors='coerce')  # Convert to datetime
 47 | df_sorted = df.sort_values(by='Period')
 48 | plt.figure(figsize=(12, 6))
 49 | plt.plot(df_sorted['Period'], df_sorted['Data_value'])
 50 | plt.title('Line Chart - Data Value over Time')
 51 | plt.xlabel('Period')
 52 | plt.ylabel('Data Value')
 53 | plt.xticks(rotation=45)
 54 | plt.tight_layout()
 55 | plt.show()
 56 | 
 57 | # -------------------------------
 58 | # Bar Plot - Data by Severity
 59 | plt.figure(figsize=(8, 6))
 60 | sns.barplot(x='Severity', y='Data_value', data=df)
 61 | plt.title('Bar Plot - Data Value by Severity')
 62 | plt.show()
 63 | 
 64 | # -------------------------------
 65 | # Column Chart - Top 10 Causes
 66 | plt.figure(figsize=(10, 6))
 67 | top_causes = df.groupby('Cause')['Data_value'].mean().sort_values(ascending=False).head(10)
 68 | top_causes.plot(kind='bar', color='skyblue')
 69 | plt.title('Top 10 Causes by Average Data Value')
 70 | plt.ylabel('Average Data Value')
 71 | plt.xticks(rotation=45)
 72 | plt.tight_layout()
 73 | plt.show()
 74 | 
 75 | # -------------------------------
 76 | # Scatter Plot - CI bounds
 77 | plt.figure(figsize=(8, 6))
 78 | sns.scatterplot(data=df, x='Lower_CI', y='Upper_CI', hue='Severity')
 79 | plt.title('Scatter Plot - Confidence Intervals by Severity')
 80 | plt.show()
 81 | 
 82 | # -------------------------------
 83 | # Pair Plot of Numeric Columns
 84 | sns.pairplot(df[numeric_cols])
 85 | plt.suptitle('Pair Plot of Numeric Variables', y=1.02)
 86 | plt.show()
 87 | 
 88 | # Info about the dataset
 89 | print("Dataset Info:")
 90 | print(df.info())
 91 | print("\nFirst 5 Rows:")
 92 | print(df.head())
 93 | 
 94 | # Check for missing values
 95 | print("\nMissing Values:\n", df.isnull().sum())
 96 | 
 97 | # -------------------------------
 98 | # Statistical Summary
 99 | numeric_cols = ['Data_value', 'Lower_CI', 'Upper_CI']
100 | print("\nStatistical Summary:\n", df[numeric_cols].describe())
101 | 
102 | # -------------------------------
103 | # Outlier Detection using Z-Score
104 | z_scores = np.abs(zscore(df[numeric_cols]))
105 | outliers = (z_scores > 3)
106 | print("\nOutliers (Z-Score > 3):\n", outliers.sum())
107 | 
108 | # -------------------------------
109 | # Correlation Heatmap
110 | plt.figure(figsize=(8, 6))
111 | sns.heatmap(df[numeric_cols].corr(), annot=True, cmap='coolwarm')
112 | plt.title('Correlation Heatmap')
113 | plt.show()
114 | 
115 | # -------------------------------
116 | # Boxplot for Outliers
117 | plt.figure(figsize=(8, 6))
118 | sns.boxplot(data=df[numeric_cols])
119 | plt.title('Boxplot - Outliers')
120 | plt.show()
121 | 
122 | # -------------------------------
123 | # Line Chart of Data over Time
124 | df['Period'] = pd.to_datetime(df['Period'], errors='coerce')  # Convert to datetime
125 | df_sorted = df.sort_values(by='Period')
126 | plt.figure(figsize=(12, 6))
127 | plt.plot(df_sorted['Period'], df_sorted['Data_value'])
128 | plt.title('Line Chart - Data Value over Time')
129 | plt.xlabel('Period')
130 | plt.ylabel('Data Value')
131 | plt.xticks(rotation=45)
132 | plt.tight_layout()
133 | plt.show()
134 | 
135 | # -------------------------------
136 | # Bar Plot - Data by Severity
137 | plt.figure(figsize=(8, 6))
138 | sns.barplot(x='Severity', y='Data_value', data=df)
139 | plt.title('Bar Plot - Data Value by Severity')
140 | plt.show()
141 | 
142 | # -------------------------------
143 | # Column Chart - Top 10 Causes
144 | plt.figure(figsize=(10, 6))
145 | top_causes = df.groupby('Cause')['Data_value'].mean().sort_values(ascending=False).head(10)
146 | top_causes.plot(kind='bar', color='skyblue')
147 | plt.title('Top 10 Causes by Average Data Value')
148 | plt.ylabel('Average Data Value')
149 | plt.xticks(rotation=45)
150 | plt.tight_layout()
151 | plt.show()
152 | 
153 | # -------------------------------
154 | # Scatter Plot - CI bounds
155 | plt.figure(figsize=(8, 6))
156 | sns.scatterplot(data=df, x='Lower_CI', y='Upper_CI', hue='Severity')
157 | plt.title('Scatter Plot - Confidence Intervals by Severity')
158 | plt.show()
159 | 
160 | # -------------------------------
161 | # Pair Plot of Numeric Columns
162 | sns.pairplot(df[numeric_cols])
163 | plt.suptitle('Pair Plot of Numeric Variables', y=1.02)
164 | plt.show()


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