Plotting Data using Matplotlib

import matplotlib.pyplot as plt

# Data
days = ['Monday', 'Tuesday', 'Wednesday', 'Thursday', 'Friday', 'Saturday', 'Sunday']
tickets_sold = [2000, 2800, 3000, 2500, 2300, 2500, 1000]

# Creating the line plot
plt.plot(days, tickets_sold, color='magenta')

# Adding title and labels
plt.title('Weekly Tickets Sales')
plt.xlabel('Day of the Week')
plt.ylabel('Tickets Sold')

# Displaying the plot
plt.show()

import pandas as pd
        
# Data about colleges and courses
data = {
    "College": ["College A", "College B", "College C", "College D", "College E",
        "College F", "College G", "College H", "College I", "College J"],
    "Science": [12, 15, 9, 13, 10, 14, 11, 8, 16, 10],
    "Commerce": [8, 10, 7, 9, 6, 11, 13, 12, 5, 14],
    "Humanities": [14, 12, 16, 11, 15, 10, 9, 14, 13, 8]
}

# Create a DataFrame
df = pd.DataFrame(data)

# Save DataFrame to CSV
df.to_csv('college_courses.csv', index=False)

import matplotlib.pyplot as plt
        
# Read the data back from the CSV file
df = pd.read_csv('college_courses.csv')

# Create a bar plot
df.plot(x='College', kind='bar', figsize=(10, 6))

# Adding titles and labels
plt.title('Number of Courses Offered by Colleges')
plt.xlabel('College')
plt.ylabel('Number of Courses')
plt.xticks(rotation=45)
plt.legend(title='Streams')

# Display the plot
plt.show()

import pandas as pd
import matplotlib.pyplot as plt

# Hypothetical data
boys_screen_time = [3, 4.5, 2, 5, 6, 3.5, 4, 5.5, 2.5, 4]
girls_screen_time = [2, 3.5, 4, 4.5, 3, 2.5, 5, 3.5, 4, 4.5]

# Creating DataFrame
data = {'Boys': boys_screen_time, 'Girls': girls_screen_time}
df = pd.DataFrame(data)

# Creating a boxplot
plt.figure(figsize=(8, 6))
df.boxplot(column=['Boys', 'Girls'])
plt.title('Screen Time of Students in Class (Boys vs Girls)')
plt.ylabel('Hours per Day')
plt.grid(False)
plt.show()

import pandas as pd
import matplotlib.pyplot as plt

# Temperature data for My City in January
min_temps = [7, 8, 6, 7, 8, 7, 6, 7, 8, 7, 6, 7, 8, 7, 6, 7, 8, 7, 6, 7, 8, 7, 6, 7, 8, 7, 6, 7, 8, 7]
max_temps = [19, 20, 18, 19, 20, 19, 18, 19, 20, 19, 18, 19, 20, 19, 18, 19, 20, 19, 18, 19, 20, 19, 18, 19, 20, 19, 18, 19, 20, 19]

# Creating a DataFrame
df = pd.DataFrame({'Min Temperature': min_temps, 'Max Temperature': max_temps})

# Creating a histogram plot
df.plot(kind='hist', bins=10, alpha=0.7)
plt.title('Temperature Distribution in My City for January')
plt.xlabel('Temperature (°C)')
plt.ylabel('Frequency')
plt.show()

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

# -----------------------------
# 1) Read the Census PCA file
# -----------------------------
# Put your file path here
path = "PCA0000_2011_MDDS.xls"

# The sheet name in this file is typically "PCA"
df = pd.read_excel(path, sheet_name="PCA")

# -----------------------------------------------
# 2) Keep only STATE level totals (TRU = Total)
# -----------------------------------------------
state_df = df[(df["Level"] == "STATE") & (df["TRU"] == "Total")].copy()
    
# ----------------------------------------------------------
# 3) Build population + compute literacy rate (Census logic)
#    Literacy Rate (%) = Literates (7+) / Population (7+) * 100
# ----------------------------------------------------------
state_df["Population"] = state_df["Total Population Person"]
state_df["Pop_0_6"] = state_df["Population in the age group 0-6 Person"]
state_df["Pop_7_plus"] = state_df["Population"] - state_df["Pop_0_6"]

state_df["Literates_7_plus"] = state_df["Literates Population Person"]
state_df["LiteracyRate"] = (state_df["Literates_7_plus"] / state_df["Pop_7_plus"]) * 100

# -------------------------------------
# 4) Add Region column (E/W/N/S mapping)
# -------------------------------------
region_map = {
    # North
    "JAMMU & KASHMIR": "North",
    "HIMACHAL PRADESH": "North",
    "PUNJAB": "North",
    "CHANDIGARH": "North",
    "UTTARAKHAND": "North",
    "HARYANA": "North",
    "NCT OF DELHI": "North",
    "RAJASTHAN": "North",
    "UTTAR PRADESH": "North",

    # East (includes North-East + eastern India)
    "BIHAR": "East",
    "SIKKIM": "East",
    "ARUNACHAL PRADESH": "East",
    "NAGALAND": "East",
    "MANIPUR": "East",
    "MIZORAM": "East",
    "TRIPURA": "East",
    "MEGHALAYA": "East",
    "ASSAM": "East",
    "WEST BENGAL": "East",
    "JHARKHAND": "East",
    "ODISHA": "East",
    "CHHATTISGARH": "East",
    "ANDAMAN & NICOBAR ISLANDS": "East",

    # West
    "MADHYA PRADESH": "West",
    "GUJARAT": "West",
    "DAMAN & DIU": "West",
    "DADRA & NAGAR HAVELI": "West",
    "MAHARASHTRA": "West",
    "GOA": "West",

    # South
    "ANDHRA PRADESH": "South",
    "KARNATAKA": "South",
    "LAKSHADWEEP": "South",
    "KERALA": "South",
    "TAMIL NADU": "South",
    "PUDUCHERRY": "South",
}

state_df["Region"] = state_df["Name"].map(region_map).fillna("North")

# ------------------------------------
# 5) Final table + export CSV
# ------------------------------------
final_df = state_df[["Name", "Population", "LiteracyRate", "Region"]].copy()
final_df.rename(columns={"Name": "State"}, inplace=True)

final_df["Population"] = final_df["Population"].astype("int64")
final_df["LiteracyRate"] = final_df["LiteracyRate"].round(2)

final_df.to_csv("state_population_literacy_region.csv", index=False)
print("Saved: state_population_literacy_region.csv")

# ------------------------------------
# 6) Scatter plots (one per region)
# ------------------------------------
regions = ["North", "South", "East", "West"]

for r in regions:
    sub = final_df[final_df["Region"] == r].copy()

    plt.figure(figsize=(8, 5))
    plt.scatter(
        sub["Population"],
        sub["LiteracyRate"],
        marker="D",                     # diamond marker
        s=np.sqrt(sub["LiteracyRate"])  # size = sqrt(literacy rate)
    )

    plt.title(f"Population vs Literacy Rate ({r} Region)")
    plt.xlabel("Population (Total Persons) (in crores)")
    plt.ylabel("Average Literacy Rate (%)")

    # Optional: label each point with the state name
    for _, row in sub.iterrows():
        plt.annotate(
            row["State"],
            (row["Population"], row["LiteracyRate"]),
            fontsize=7,
            xytext=(3, 3),
            textcoords="offset points"
        )

    plt.tight_layout()
    plt.show()

# ------------------------------------
# 7) Bar chart: average literacy by region
# ------------------------------------
avg_lit = final_df.groupby("Region", as_index=False)["LiteracyRate"].mean()

plt.figure(figsize=(7, 4.5))
plt.bar(avg_lit["Region"], avg_lit["LiteracyRate"])

plt.title("Average Literacy Rate by Region (Census 2011 PCA)")
plt.xlabel("Region")
plt.ylabel("Average Literacy Rate (%)")


plt.tight_layout()
plt.show()