1️⃣ Time Series Trend Graph (Correct Way)
Python Code:
import pandas as pd
import matplotlib.pyplot as plt
df['Date'] = pd.to_datetime(df['Date'])
plt.figure(figsize=(10,5))
plt.plot(df['Date'], df['Price'])
plt.title("Time Series Trend")
plt.xlabel("Date")
plt.ylabel("Price")
plt.xticks(rotation=45)
plt.show()
Output:
✅ When We Use It:
- When data has date / time column
- Before applying ARIMA, SARIMA, LSTM
- To check trend and pattern over years
🎯 Why We Use It:
- To see upward/downward trend
- To detect structural breaks
- To identify seasonality
- To check if data is stationary
2️⃣ Multiple Line Comparison Graph
Python Code:
plt.figure(figsize=(10,5)) plt.plot(df['Date'], df['Min_Price'], label="Min Price") plt.plot(df['Date'], df['Max_Price'], label="Max Price") plt.plot(df['Date'], df['Modal_Price'], label="Modal Price") plt.legend() plt.xticks(rotation=45) plt.show()
Output:
✅ When We Use It:
- When comparing Min, Max, Modal prices
- When comparing multiple variables over time
🎯 Why We Use It:
- To check spread between values
- To analyze volatility
- To see if variables move together
- To detect market instability
3️⃣ Monthly Seasonal Pattern Graph
Python Code:
df['Month'] = df['Date'].dt.month
monthly_avg = df.groupby('Month')['Price'].mean()
plt.figure(figsize=(8,5))
plt.plot(monthly_avg.index, monthly_avg.values)
plt.title("Monthly Seasonal Pattern")
plt.xlabel("Month")
plt.ylabel("Average Price")
plt.show()
Output:
✅ When We Use It:
- When data spans multiple years
- When checking seasonality
- Before applying SARIMA
🎯 Why We Use It:
- To confirm seasonal pattern
- To understand cyclic behavior
- To detect repeating trends
4️⃣ Scatter Plot (Correlation Check)
Python Code:
plt.figure(figsize=(6,5))
plt.scatter(df['Min_Price'], df['Max_Price'])
plt.xlabel("Min Price")
plt.ylabel("Max Price")
plt.show()
Output:
✅ When We Use It:
- Before Linear Regression
- To check relationship between variables
- For feature selection
🎯 Why We Use It:
- To detect correlation
- To check linearity
- To detect outliers
- To avoid useless predictors
5️⃣ Histogram (Distribution Check)
Python Code:
plt.figure(figsize=(6,5))
plt.hist(df['Price'], bins=30)
plt.xlabel("Price")
plt.ylabel("Frequency")
plt.show()
Output:
✅ When We Use It:
- During EDA
- Before regression modeling
- To check normality
🎯 Why We Use It:
- To check skewness
- To detect heavy tails
- To decide transformation
6️⃣ Box Plot (Outlier Detection)
Python Code:
plt.figure(figsize=(6,5)) plt.boxplot(df['Price']) plt.show()
Output:
✅ When We Use It:
- Before cleaning dataset
- To detect extreme values
- During preprocessing
🎯 Why We Use It:
- Shows median
- Shows IQR
- Detects outliers visually
- Helps cleaning decision
7️⃣ Correlation Matrix Heatmap
Python Code:
import seaborn as sns plt.figure(figsize=(8,6)) corr = df.corr() sns.heatmap(corr, annot=True) plt.show()
Output:
✅ When We Use It:
- Before ML modeling
- When multiple numeric features exist
- For feature selection
🎯 Why We Use It:
- To detect multicollinearity
- To remove redundant variables
- To choose best predictors
- To improve model accuracy
1️⃣ LINE PLOT (Most Important for You)
Python Code
plt.figure(figsize=(10,5))
plt.plot(data["Month"],
data["Modal Price (Rs./Quintal)"],
marker="o",
linewidth=2)
plt.xlabel("Month")
plt.ylabel("Modal Price")
plt.title("Monthly Modal Price Trend")
plt.show()
Explanation of Each Function
| Function | What It Does |
|---|---|
| plt.figure(figsize=(10,5)) | Sets graph size |
| plt.plot(x,y) | Creates line graph |
| marker="o" | Adds circle dots |
| linewidth=2 | Controls line thickness |
| plt.xlabel() | Name of X-axis |
| plt.ylabel() | Name of Y-axis |
| plt.title() | Graph title |
| plt.show() | Displays graph |
When We Use Line Plot?
- Time series data
- Monthly/Yearly crop prices
- Trend analysis
- Forecasting models (ARIMA, LSTM)
Because your crop price dataset is time-based. It helps to see trends, seasonality, and price movement.
2️⃣ HISTOGRAM
Python Code
plt.hist(data["Modal Price (Rs./Quintal)"],
bins=10,
edgecolor="black")
plt.xlabel("Modal Price")
plt.ylabel("Frequency")
plt.title("Distribution of Modal Price")
plt.show()
Explanation
| Function | What It Does |
|---|---|
| plt.hist() | Creates histogram |
| bins=10 | Divides data into 10 ranges |
| edgecolor | Border color of bars |
When We Use Histogram?
- To check data distribution
- Before normalization
- Before regression models
- To detect skewness
Histogram helps check if data is normally distributed and whether outliers exist.
3️⃣ SCATTER PLOT
Python Code
plt.scatter(data["Min Price (Rs./Quintal)"],
data["Max Price (Rs./Quintal)"])
plt.xlabel("Min Price")
plt.ylabel("Max Price")
plt.title("Min vs Max Price Relationship")
plt.show()
When We Use Scatter Plot?
- Check relationship between two variables
- Before regression
- Correlation checking
If points move upward → Positive correlation
If downward → Negative correlation
If random → No strong relation
4️⃣ BAR GRAPH
Python Code
yearly_avg = data.groupby("Year")["Modal Price (Rs./Quintal)"].mean()
plt.bar(yearly_avg.index,
yearly_avg.values)
plt.xlabel("Year")
plt.ylabel("Average Modal Price")
plt.title("Yearly Average Modal Price")
plt.show()
When We Use Bar Graph?
- Compare categories
- Compare yearly performance
- Compare ML model metrics
Bar graph is best for comparison of categories and yearly averages.
5️⃣ STACK / AREA PLOT
Python Code
plt.stackplot(data["Month"],
data["Min Price (Rs./Quintal)"],
data["Modal Price (Rs./Quintal)"],
data["Max Price (Rs./Quintal)"],
labels=["Min", "Modal", "Max"])
plt.xlabel("Month")
plt.ylabel("Price")
plt.title("Price Comparison Area Plot")
plt.legend()
plt.show()
When We Use It?
- Compare contribution
- Show composition of multiple variables
Shows which price component dominates over time.
6️⃣ PIE CHART
Python Code
avg_prices = [
data["Min Price (Rs./Quintal)"].mean(),
data["Modal Price (Rs./Quintal)"].mean(),
data["Max Price (Rs./Quintal)"].mean()
]
labels = ["Min", "Modal", "Max"]
plt.pie(avg_prices,
labels=labels,
autopct="%1.1f%%")
plt.title("Average Price Contribution")
plt.show()
When We Use It?
- To show percentage distribution
- For presentation
- For reports
Pie chart shows percentage contribution of each price component.