└── Agricultural Land use in india


/Agricultural Land use in india:
--------------------------------------------------------------------------------
  1 | import pandas as pd
  2 | import numpy as np
  3 | import matplotlib.pyplot as plt
  4 | import seaborn as sns
  5 | import warnings
  6 | warnings.filterwarnings("ignore")
  7 | 
  8 | # Load dataset
  9 | df = pd.read_csv(r"C:\Users\Asus\OneDrive\Desktop\ProjectData.csv")
 10 | print(df.info())
 11 | print(df.describe())
 12 | 
 13 | # Check for missing values
 14 | print("\nMissing values in each column:\n", df.isna().sum()) #checking per col.
 15 | 
 16 | # Check column names
 17 | print("Columns:", df.columns.tolist())
 18 | 
 19 | # Chart 1: Histogram - Net Area Sown
 20 | plt.figure(figsize=(8, 5))
 21 | sns.histplot(df['Net area sown'], bins=25, kde=True, color='skyblue')
 22 | plt.title('Distribution of Net Area Sown')
 23 | plt.xlabel('Net Area Sown')
 24 | plt.ylabel('Count')
 25 | plt.tight_layout()
 26 | plt.show()
 27 | 
 28 | # Chart 2: Bar Plot - Mean Net Area Cultivated by Category of Holdings
 29 | plt.figure(figsize=(7, 5))
 30 | mean_values = df.groupby('Category of holdings')['Net area cultivated'].mean().sort_values(ascending=False)
 31 | sns.barplot(x=mean_values.index, y=mean_values.values, palette='viridis')
 32 | plt.title('Average Net Area Cultivated by Category of Holdings')
 33 | plt.ylabel('Mean Net Area Cultivated')
 34 | plt.xticks(rotation=45)
 35 | plt.tight_layout()
 36 | plt.show()
 37 | 
 38 | # Chart 3: Barplot - Mean Net Area Sown by State
 39 | state_avg = df.groupby('srcStateName')['Net area sown'].mean().sort_values(ascending=False).head(10)
 40 | plt.figure(figsize=(10, 6))
 41 | sns.barplot(x=state_avg.values, y=state_avg.index, palette='viridis')
 42 | plt.title('Top 10 States by Mean Net Area Sown')
 43 | plt.xlabel('Mean Net Area Sown')
 44 | plt.ylabel('State')
 45 | plt.tight_layout()
 46 | plt.show()
 47 | 
 48 | # Chart 4: Pie Chart - Distribution of Category of Holdings
 49 | cat_counts = df['Category of holdings'].value_counts()
 50 | plt.figure(figsize=(6, 6))
 51 | plt.pie(cat_counts, labels=cat_counts.index, autopct='%1.1f%%', startangle=140)
 52 | plt.title('Distribution of Land Holdings Categories')
 53 | plt.tight_layout()
 54 | plt.show()
 55 | 
 56 | 
 57 | 
 58 | # Chart 5: Correlation Heatmap
 59 | num_cols = ['Net area sown', 'Area under current fallows', 'Net area cultivated', 'Uncultivated area ']
 60 | corr = df[num_cols].corr()
 61 | plt.figure(figsize=(8, 6))
 62 | sns.heatmap(corr, annot=True, cmap='coolwarm', fmt='.2f', linewidths=0.5,
 63 |             linecolor='gray', square=True, cbar_kws={'shrink': 0.5})
 64 | plt.title('Correlation Heatmap of Area Features', fontsize=14, fontweight='bold')
 65 | plt.tight_layout()
 66 | plt.show()
 67 | 
 68 | 
 69 | #chart 6:  Create a box plot for 'Value' grouped by 'Group'
 70 | plt.figure(figsize=(8, 6))
 71 | sns.boxplot(x='Category of holdings', y='Social group type', data=df, palette='Set2')
 72 | plt.title('Box Plot of Values by Group')
 73 | plt.xlabel('Group')
 74 | plt.ylabel('Value')
 75 | plt.tight_layout()
 76 | plt.show()
 77 | 
 78 | 
 79 | #chart 7:  Create the scatter plot
 80 | plt.figure(figsize=(8, 6))
 81 | sns.scatterplot(data=df, x='Net area sown', y='Net area cultivated', hue='Category of holdings', palette='viridis')
 82 | plt.title('Scatter Plot: Net Area Sown vs Net Area Cultivated')
 83 | plt.xlabel('Net area sown')
 84 | plt.ylabel('Net area cultivated')
 85 | plt.tight_layout()
 86 | plt.show()
 87 | 
 88 | # --- Linear Regression ----
 89 | 
 90 | # Prepare features and target variable
 91 | x = df['Net area sown'].values
 92 | y = df['Net area cultivated'].values
 93 | 
 94 | 
 95 | # Manual train-test split using pandas
 96 | train = df.sample(frac=0.8, random_state=42)
 97 | test = df.drop(train.index)
 98 | x_train = train['Net area sown'].values
 99 | y_train = train['Net area cultivated'].values
100 | x_test = test['Net area sown'].values
101 | y_test = test['Net area cultivated'].values
102 | 
103 | # Fit linear regression using NumPy's polyfit on the training set
104 | slope, intercept = np.polyfit(x_train, y_train, 1)
105 | 
106 | # Prediction example for Net area sown = 5000
107 | pred_5000 = slope * 5000 + intercept
108 | print("Predicted Net Area Cultivated for 5000 Net Area Sown:", pred_5000)
109 | 
110 | 
111 | 
112 | # Plot regression line 
113 | plt.figure(figsize=(8, 5))
114 | plt.scatter(x, y, color="green", label="Data Points")
115 | plt.plot(x, slope * x + intercept, color='red', linewidth=3, label="Regression Line")
116 | plt.xlabel("Net area sown")
117 | plt.ylabel("Net area cultivated")
118 | plt.title("Linear Regression Fit")
119 | plt.legend()
120 | plt.tight_layout()
121 | plt.show()
122 | 


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