Project Based Learning

import pandas as pd
import matplotlib.pyplot as plt

mer = pd.read_csv("merchandise.csv")
vis = pd.read_csv("visits.csv")
ord = pd.read_csv("orders.csv")

# 1) Monthly revenue generation
monthly_rev = ord.groupby("Month")["FinalAmount"].sum().sort_index()
print(monthly_rev)

# 2) Category wise sales
cat_sales = ord.groupby(["GenderCategory","SubCategory"])["FinalAmount"].sum()
print(cat_sales)

# 3) Event-wise revenue (mega events focus)
event_rev = ord.groupby("Event")["FinalAmount"].sum()
print(event_rev)

# 4) Conversion rate (customers visiting vs placing order)
total_visits = len(vis)
total_orders = (vis["DidOrder"] == "Y").sum()
conversion_rate = (total_orders / total_visits) * 100
print("Conversion Rate:", round(conversion_rate, 2), "%")

# Plots (as asked: “plotted appropriately”)
monthly_rev.plot(kind="bar")
plt.title("Monthly Revenue Generation")
plt.ylabel("Revenue (₹)")
plt.show()

event_rev.plot(kind="bar")
plt.title("Revenue During Mega Events")
plt.ylabel("Revenue (₹)")
plt.show()

import pandas as pd
import matplotlib.pyplot as plt

# ---------- Step 1: Read CSV files ----------
collections = pd.read_csv("collections.csv")
refurbished = pd.read_csv("refurbished.csv")
orders = pd.read_csv("orders.csv")

# ---------- Step 2: Basic validation (as per specification) ----------
allowed_conditions = {"Fit", "Needs mending", "Needs Mending", "Unfit"}

# Condition validation
bad_conditions = collections[~collections["Condition"].isin(allowed_conditions)]
if not bad_conditions.empty:
    print("Invalid conditions found:\n", bad_conditions)

# ID prefix validation
bad_book_ids = collections[(collections["Item category"] == "Book") & (~collections["Item ID"].astype(str).str.startswith("B"))]
bad_notebook_ids = collections[(collections["Item category"] == "Notebook") & (~collections["Item ID"].astype(str).str.startswith("N"))]
if not bad_book_ids.empty:
    print("Invalid Book IDs:\n", bad_book_ids)
if not bad_notebook_ids.empty:
    print("Invalid Notebook IDs:\n", bad_notebook_ids)

# ---------- Step 3: Items collected (counts) ----------
collected_by_category = collections.groupby("Item category")["Item ID"].count()
collected_by_condition = collections.groupby("Condition")["Item ID"].count()

print("Collected by category:\n", collected_by_category)
print("Collected by condition:\n", collected_by_condition)

# ---------- Step 4: Items refurbished (quantity) ----------
refurbished_qty = refurbished.groupby("Item Category")["Quantity"].sum()
print("Refurbished quantity by category:\n", refurbished_qty)

# ---------- Step 5: Sales (revenue) ----------
orders["Revenue"] = orders["Quantity"] * orders["Price"]
sales_by_category = orders.groupby("Item Category")["Revenue"].sum()
print("Sales (revenue) by category:\n", sales_by_category)

# ---------- Step 6: Update refurbished stock after orders ----------
# We update by matching (Item Category + Item name)
# (In real software, Item id would be best for matching.)
stock = refurbished.copy()
stock_key = stock["Item Category"].astype(str) + "||" + stock["Item name"].astype(str)
order_key = orders["Item Category"].astype(str) + "||" + orders["Item name"].astype(str)

stock["key"] = stock_key
orders["key"] = order_key

ordered_qty = orders.groupby("key")["Quantity"].sum().reset_index()

# Merge ordered qty into stock and subtract
stock = stock.merge(ordered_qty, on="key", how="left", suffixes=("", "_ordered"))
stock["Quantity_ordered"] = stock["Quantity_ordered"].fillna(0).astype(int)
stock["Quantity"] = stock["Quantity"] - stock["Quantity_ordered"]

# Ensure quantity does not go negative
stock.loc[stock["Quantity"] < 0, "Quantity"] = 0

# Save updated stock
stock.drop(columns=["key", "Quantity_ordered"]).to_csv("refurbished_updated.csv", index=False)

# ---------- Step 7: Plots (as required) ----------
plt.figure()
collected_by_category.plot(kind="bar")
plt.title("Items Collected (Count) by Item Category")
plt.ylabel("Count")
plt.tight_layout()
plt.show()

plt.figure()
refurbished_qty.plot(kind="bar")
plt.title("Items Refurbished (Total Quantity) by Category")
plt.ylabel("Quantity")
plt.tight_layout()
plt.show()

plt.figure()
sales_by_category.plot(kind="bar")
plt.title("Sales (Total Revenue) by Category")
plt.ylabel("Revenue (₹)")
plt.tight_layout()
plt.show()

# Optional: by condition
plt.figure()
collected_by_condition.plot(kind="bar")
plt.title("Collected Items by Condition")
plt.ylabel("Count")
plt.tight_layout()
plt.show()

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

# -----------------------------
# Step 1: Read CSV into DataFrame
# -----------------------------
# Example filename exported from Google Forms:
df = pd.read_csv("social_media_survey_responses.csv")

# (Optional) If DailyHours is stored as ranges like "2–3 hours",
# convert it into numeric hours (approx midpoint) before analysis.

# -----------------------------
# Step 2: Statistical computations (mean, median, etc.)
# -----------------------------
print("Mean DailyHours:", df["DailyHours"].mean())
print("Median DailyHours:", df["DailyHours"].median())
print("Mean SleepHours:", df["SleepHours"].mean())
print("Median SleepHours:", df["SleepHours"].median())

# -----------------------------
# Step 3: Prepare analysis groups
# -----------------------------
df["UsageGroup"] = np.where(df["DailyHours"] >= 3, "High (>=3h/day)", "Low (<3h/day)")
group_stats = df.groupby("UsageGroup")[["DailyHours","SleepHours","MoodScore","ConcentrationScore"]].mean()
print("\nHigh vs Low usage comparison:\n", group_stats)

# -----------------------------
# Step 4: Visualise findings using charts
# -----------------------------

# Chart 1: Daily hours distribution (bins)
bins = [0, 1, 2, 3, 4, 5, 6]
labels = ["0-1", "1-2", "2-3", "3-4", "4-5", "5-6"]
df["HoursBin"] = pd.cut(df["DailyHours"], bins=bins, labels=labels, include_lowest=True, right=False)
hours_dist = df["HoursBin"].value_counts().reindex(labels).fillna(0)

plt.figure()
hours_dist.plot(kind="bar")
plt.title("Daily Time on Social Networking Sites (Hours/Day)")
plt.xlabel("Hours (binned)")
plt.ylabel("Number of students")
plt.tight_layout()
plt.show()

# Chart 2: Most used platform
plt.figure()
df["MainPlatform"].value_counts().plot(kind="bar")
plt.title("Most Used Social Networking Platform")
plt.xlabel("Platform")
plt.ylabel("Number of students")
plt.tight_layout()
plt.show()

# Chart 3: Daily hours vs sleep hours (scatter)
plt.figure()
plt.scatter(df["DailyHours"], df["SleepHours"])
plt.title("Daily Social Media Hours vs Sleep Hours")
plt.xlabel("Daily social media time (hours)")
plt.ylabel("Sleep per night (hours)")
plt.tight_layout()
plt.show()

# Chart 4: Mood by usage group
plt.figure()
df.groupby("UsageGroup")["MoodScore"].mean().plot(kind="bar")
plt.title("Average Mood Score by Usage Group")
plt.xlabel("Usage group")
plt.ylabel("Average Mood Score (1-5)")
plt.tight_layout()
plt.show()

# Chart 5: Anxiety frequency distribution
order = ["Never","Rarely","Sometimes","Often"]
plt.figure()
df["AnxietyFrequency"].value_counts().reindex(order).fillna(0).plot(kind="bar")
plt.title("Anxiety Frequency (Self-reported)")
plt.xlabel("Frequency")
plt.ylabel("Number of students")
plt.tight_layout()
plt.show()

import pandas as pd
import matplotlib.pyplot as plt

# add correct path on your computer
data = pd.read_csv("PCA_AY_2011_Revised.csv")
df = pd.DataFrame(data)

print(df.shape)

12168 rows and 123 columns.

print(df.columns.values)

['Table No.'
'State Code'
'District Code'
'Area Name'
'Total/ Rural/ Urban'
'Adolescent and youth categories'
'Total Population - Persons'
'Total Population - Males'
'Total Population - Females'
'Scheduled Caste - Persons'
'Scheduled Caste - Males'
........................
........................
........................
'Scheduled Tribe Marginal Worker - Household Industry - Males'
'Scheduled Tribe Marginal Worker - Household Industry - Females'
'Scheduled Tribe Marginal Worker - Other Workers - Persons'
'Scheduled Tribe Marginal Worker - Other Workers - Males'
'Scheduled Tribe Marginal Worker - Other Workers - Females']

print(df['Area Name'])

0            INDIA
1            INDIA
2            INDIA
3            INDIA
4            INDIA
...................
...................
...................
12163       District - South Andaman (03)
12164       District - South Andaman (03)
12165       District - South Andaman (03)
12166       District - South Andaman (03)
12167       District - South Andaman (03)
Name: Area Name, Length: 12168, dtype: object

df1 = df.loc[(df["Area Name"] == "INDIA"),
    "Area Name": "Total Population - Females"]

df1.columns = ["Area",
    "Class",
    "Category",
    "TotalPop",
    "MalePop",
    "FemalePop"]

d = df1.groupby("Category").sum(numeric_only=True)

# keep only the age groups needed for 10–24
d = d.drop(["Adolescent (10-19)", "All Ages", "Youth (15-24)"], axis=0)

| Category |    TotalPop |     MalePop |   FemalePop |
| -------- | ----------- | ----------- | ----------- |
| 10-14    | 26,54,18,424 | 13,88,37,670 | 12,65,80,754 |
| 15-19    | 24,10,52,898 | 12,79,64,792 | 11,30,88,106 |
| 20-24    | 22,28,48,444 | 11,51,69,386 | 10,76,79,058 |

d.plot(kind="bar")
plt.show()

import pandas as pd
import matplotlib.pyplot as plt

# Step 1
data = pd.read_csv("PCA_AY_2011_Revised.csv")   # add correct path on your computer
df = pd.DataFrame(data)

# Step 2
print(df.shape)

# Step 3
print(df.columns.values)

# Step 4 (understanding data)
print(df["Area Name"])

# Step 5 (filter India rows + required columns)
df1 = df.loc[(df["Area Name"] == "INDIA"), "Area Name":"Total Population - Females"]

# Step 6 (rename)
df1.columns = ["Area", "Class", "Category", "TotalPop", "MalePop", "FemalePop"]

# Step 7 (group and keep only 10–24 categories)
d = df1.groupby("Category").sum(numeric_only=True)
d = d.drop(["Adolescent (10-19)", "All Ages", "Youth (15-24)"], axis=0)

print(d)

# Step 8 (plot)
d.plot(kind="bar")
plt.xlabel("Adolescent and youth categories")
plt.ylabel("Population (in crores)")
plt.title("Population (10–24 years) in India: Total, Male, Female")
plt.tight_layout()
plt.show()

import pandas as pd

# add correct path on your computer
df = pd.read_csv("PCA_AY_2011_Revised.csv")

df1 = df.loc[
    (df["District Code"] == 0) &
    (df["Area Name"] != "INDIA"),
    (df["Total/ Rural/ Urban"] == "Total") &
    (df["Adolescent and youth categories"] == "Youth (15-24)")
].copy()

df1["Illiterates - Youth - Persons"] = (
    df1["Total Population - Persons"] - df1["Literates - Total - Persons"]
)

state_ill = df1.groupby("Area Name")["Illiterates - Youth - Persons"].sum().sort_values(ascending=False)
max_state = state_ill.index[0]
max_value = int(state_ill.iloc[0])

max_state, max_value

import pandas as pd

df = pd.read_csv("PCA_AY_2011_Revised.csv")

print(df.shape)

12168 rows × 123 columns

Because the question asks for “people” (overall), we take INDIA, Total, All Ages.

df_india = df[
    (df["Area Name"] == "INDIA") &
    (df["Total/ Rural/ Urban"] == "Total") &
    (df["Adolescent and youth categories"] == "All Ages")
][["Main Worker - Total - Persons", "Marginal Worker - Total - Persons"]].copy()

main_workers = int(df_india.iloc[0]["Main Worker - Total - Persons"])
marg_workers = int(df_india.iloc[0]["Marginal Worker - Total - Persons"])
total_workers = main_workers + marg_workers

marginal_worker_percent = (marg_workers / total_workers) * 100
print(round(marginal_worker_percent, 2))

import pandas as pd

df = pd.read_csv("PCA_AY_2011_Revised.csv")

# Filter INDIA, Total, All Ages
df_india = df[
    (df["Area Name"] == "INDIA") &
    (df["Total/ Rural/ Urban"] == "Total") &
    (df["Adolescent and youth categories"] == "All Ages")
][["Main Worker - Total - Persons", "Marginal Worker - Total - Persons"]].copy()

main_workers = int(df_india.iloc[0]["Main Worker - Total - Persons"])
marg_workers = int(df_india.iloc[0]["Marginal Worker - Total - Persons"])
total_workers = main_workers + marg_workers

marginal_worker_percent = (marg_workers / total_workers) * 100

print("Main workers (Persons):", main_workers)
print("Marginal workers (Persons):", marg_workers)
print("Total workers (Persons):", total_workers)
print("Marginal worker percentage:", round(marginal_worker_percent, 2), "%")

import pandas as pd
import matplotlib.pyplot as plt

df = pd.read_csv("PCA_AY_2011_Revised.csv")

df_state = df[
    (df["District Code"] == 0) &
    (df["Area Name"] != "INDIA") &
    (df["Total/ Rural/ Urban"] == "Total") &
    (df["Adolescent and youth categories"] == "All Ages")
][["Area Name", "Marginal Worker - Total - Persons"]].copy()

import pandas as pd
import matplotlib.pyplot as plt

df = pd.read_csv("PCA_AY_2011_Revised.csv")

df_state = df[
    (df["District Code"] == 0) &
    (df["Area Name"] != "INDIA") &
    (df["Total/ Rural/ Urban"] == "Total") &
    (df["Adolescent and youth categories"] == "All Ages")
][["Area Name", "Marginal Worker - Total - Persons"]].copy()

top5 = df_state.sort_values("Marginal Worker - Total - Persons", ascending=False).head(5)

print("Top 5 States/UTs by Marginal Workers (Persons):")
print(top5)

# Bar chart (helpful visual)
plt.figure()
plt.bar(top5["Area Name"], top5["Marginal Worker - Total - Persons"])
plt.title("Top 5 States/UTs: Marginal Workers (All Ages, Total)")
plt.xlabel("State / Union Territory")
plt.ylabel("Marginal Workers (Persons)")
plt.xticks(rotation=60, ha="right")
plt.tight_layout()
plt.show()

import pandas as pd
import matplotlib.pyplot as plt

df = pd.read_csv("PCA_AY_2011_Revised.csv")

df_ru = df[
    (df["Area Name"] == "INDIA") &
    (df["Adolescent and youth categories"] == "All Ages") &
    (df["Total/ Rural/ Urban"].isin(["Rural", "Urban"]))
][["Total/ Rural/ Urban", "Total Population - Males", "Total Population - Females"]].copy()

df_ru.columns = ["Class", "MalePop", "FemalePop"]

g = df_ru.groupby("Class")[["MalePop", "FemalePop"]].sum()
g["SexRatio"] = (g["FemalePop"] / g["MalePop"]) * 1000
result = g.reset_index()
print(result)

plt.figure()
plt.bar(result["Class"], result["SexRatio"])
plt.title("Sex Ratio (Females per 1000 Males): Urban vs Rural (INDIA, All Ages)")
plt.xlabel("Area type")
plt.ylabel("Sex Ratio")
plt.tight_layout()
plt.show()

# Project IV - Task 5 (Consolidated Code)
# Compare sex ratio of Urban vs Rural areas (INDIA) using a graph

import pandas as pd
import matplotlib.pyplot as plt

# Read the dataset (use the .xlsx-converted version for reliable reading)
df = pd.read_csv("PCA_AY_2011_Revised.csv")

# Filter: INDIA + All Ages + Rural/Urban only
df_ru = df[
    (df["Area Name"] == "INDIA") &
    (df["Adolescent and youth categories"] == "All Ages") &
    (df["Total/ Rural/ Urban"].isin(["Rural", "Urban"]))
][["Total/ Rural/ Urban", "Total Population - Males", "Total Population - Females"]].copy()

# Rename columns for ease
df_ru.columns = ["Class", "MalePop", "FemalePop"]

# Group (safety) and compute Sex Ratio = (Female/Male)*1000
g = df_ru.groupby("Class")[["MalePop", "FemalePop"]].sum()
g["SexRatio"] = (g["FemalePop"] / g["MalePop"]) * 1000

# Final data points
result = g.reset_index()
print("Data points used (Urban vs Rural):")
print(result)

# Plot (required by the question)
plt.figure()
plt.bar(result["Class"], result["SexRatio"])
plt.title("Sex Ratio (Females per 1000 Males): Urban vs Rural (INDIA, All Ages)")
plt.xlabel("Area type")
plt.ylabel("Sex Ratio")
plt.tight_layout()
plt.show()

import pandas as pd
import numpy as np

df = pd.read_csv("PCA_AY_2011_Revised.csv")

state_df = df[
    (df["District Code"] == 0) &
    (df["Area Name"] != "INDIA") &
    (df["Total/ Rural/ Urban"] == "Total") &
    (df["Adolescent and youth categories"] == "All Ages")
][[
    "Area Name",
    "Scheduled Tribe - Persons",
    "Literates - Scheduled Tribe - Persons",
    "Scheduled Caste - Persons",
    "Literates - Scheduled Caste - Persons"
]].copy()

state_df["ST_Literate_Pct"] = np.where(
    state_df["Scheduled Tribe - Persons"] > 0,
    (state_df["Literates - Scheduled Tribe - Persons"] / state_df["Scheduled Tribe - Persons"]) * 100,
    np.nan
)

state_df["SC_Literate_Pct"] = np.where(
    state_df["Scheduled Caste - Persons"] > 0,
    (state_df["Literates - Scheduled Caste - Persons"] / state_df["Scheduled Caste - Persons"]) * 100,
    np.nan
)

st_valid = state_df.dropna(subset=["ST_Literate_Pct"])
sc_valid = state_df.dropna(subset=["SC_Literate_Pct"])

st_high = st_valid.loc[st_valid["ST_Literate_Pct"].idxmax()]
st_low  = st_valid.loc[st_valid["ST_Literate_Pct"].idxmin()]

sc_high = sc_valid.loc[sc_valid["SC_Literate_Pct"].idxmax()]
sc_low  = sc_valid.loc[sc_valid["SC_Literate_Pct"].idxmin()]

import pandas as pd
import numpy as np

df = pd.read_csv("PCA_AY_2011_Revised.csv")

state_df = df[
    (df["District Code"] == 0) &
    (df["Area Name"] != "INDIA") &
    (df["Total/ Rural/ Urban"] == "Total") &
    (df["Adolescent and youth categories"] == "All Ages")
][[
    "Area Name",
    "Scheduled Tribe - Persons",
    "Literates - Scheduled Tribe - Persons",
    "Scheduled Caste - Persons",
    "Literates - Scheduled Caste - Persons"
]].copy()

state_df["ST_Literate_Pct"] = np.where(
    state_df["Scheduled Tribe - Persons"] > 0,
    (state_df["Literates - Scheduled Tribe - Persons"] / state_df["Scheduled Tribe - Persons"]) * 100,
    np.nan
)

state_df["SC_Literate_Pct"] = np.where(
    state_df["Scheduled Caste - Persons"] > 0,
    (state_df["Literates - Scheduled Caste - Persons"] / state_df["Scheduled Caste - Persons"]) * 100,
    np.nan
)

st_valid = state_df.dropna(subset=["ST_Literate_Pct"])
sc_valid = state_df.dropna(subset=["SC_Literate_Pct"])

st_high = st_valid.loc[st_valid["ST_Literate_Pct"].idxmax()]
st_low  = st_valid.loc[st_valid["ST_Literate_Pct"].idxmin()]
sc_high = sc_valid.loc[sc_valid["SC_Literate_Pct"].idxmax()]
sc_low  = sc_valid.loc[sc_valid["SC_Literate_Pct"].idxmin()]

print("ST Highest:", st_high["Area Name"], round(st_high["ST_Literate_Pct"], 2))
print("ST Lowest :", st_low["Area Name"], round(st_low["ST_Literate_Pct"], 2))
print("SC Highest:", sc_high["Area Name"], round(sc_high["SC_Literate_Pct"], 2))
print("SC Lowest :", sc_low["Area Name"], round(sc_low["SC_Literate_Pct"], 2))

import pandas as pd
import matplotlib.pyplot as plt

df = pd.read_csv("PCA_AY_2011_Revised.csv")

state_df = df[
    (df["District Code"] == 0) &
    (df["Area Name"] != "INDIA") &
    (df["Total/ Rural/ Urban"] == "Total") &
    (df["Adolescent and youth categories"] == "All Ages")
][[
    "Area Name",
    "Marginal Worker - Total - Males",
    "Marginal Worker - Total - Females"
]].copy()

import pandas as pd
import matplotlib.pyplot as plt

# Read dataset (converted from the uploaded .xls)
df = pd.read_csv("PCA_AY_2011_Revised.csv")

# Filter: State/UT totals, Total, All Ages; exclude INDIA
state_df = df[
    (df["District Code"] == 0) &
    (df["Area Name"] != "INDIA") &
    (df["Total/ Rural/ Urban"] == "Total") &
    (df["Adolescent and youth categories"] == "All Ages")
][[
    "Area Name",
    "Marginal Worker - Total - Males",
    "Marginal Worker - Total - Females"
]].copy()

state_df = state_df.rename(columns={
    "Area Name": "State/UT",
    "Marginal Worker - Total - Males": "MaleMarginalWorkers",
    "Marginal Worker - Total - Females": "FemaleMarginalWorkers"
})

# Sort for cleaner plotting
state_df["TotalMarginalWorkers"] = state_df["MaleMarginalWorkers"] + state_df["FemaleMarginalWorkers"]
state_df = state_df.sort_values("TotalMarginalWorkers", ascending=False).reset_index(drop=True)

# Plot (stacked bar, good for many states/UTs)
plt.figure(figsize=(16, 7))
x = range(len(state_df))
plt.bar(x, state_df["MaleMarginalWorkers"], label="Male marginal workers")
plt.bar(
    x,
    state_df["FemaleMarginalWorkers"],
    bottom=state_df["MaleMarginalWorkers"],
    label="Female marginal workers"
)

plt.title("State/UT-wise Marginal Workers: Male vs Female (All Ages, Total)")
plt.xlabel("State / Union Territory")
plt.ylabel("Number of marginal workers (persons)")
plt.xticks(list(x), state_df["State/UT"], rotation=90)
plt.tight_layout()
plt.show()

# Optional: print top 10 for quick discussion
print(state_df.head(10)[["State/UT","MaleMarginalWorkers","FemaleMarginalWorkers","TotalMarginalWorkers"]])

import pandas as pd
import matplotlib.pyplot as plt

df = pd.read_excel("PCA_AY_2011_Revised.csv")

df_india = df[
    (df["Area Name"] == "INDIA") &
    (df["Adolescent and youth categories"] == "All Ages") &
    (df["Total/ Rural/ Urban"].isin(["Total", "Urban"]))
][[
    "Total/ Rural/ Urban",
    "Scheduled Tribe - Persons",
    "Literates - Scheduled Tribe - Persons"
]].copy()

df_india.columns = ["Class", "ST_Persons", "ST_Literate"]
df_india["ST_Illiterate"] = df_india["ST_Persons"] - df_india["ST_Literate"]

urban_lit = 7003778
urban_illit = 3458094

plt.figure()
plt.pie(
    [urban_lit, urban_illit],
    labels=["Literate ST (Urban)", "Illiterate ST (Urban)"],
    autopct="%1.1f%%"
)
plt.title("Scheduled Tribes in Urban Areas (INDIA, All Ages): Literate vs Illiterate")
plt.tight_layout()
plt.show()

import pandas as pd
import matplotlib.pyplot as plt

df = pd.read_csv("PCA_AY_2011_Revised.csv")

# Filter: INDIA, All Ages, Total + Urban
df_india = df[
    (df["Area Name"] == "INDIA") &
    (df["Adolescent and youth categories"] == "All Ages") &
    (df["Total/ Rural/ Urban"].isin(["Total", "Urban"]))
][[
    "Total/ Rural/ Urban",
    "Scheduled Tribe - Persons",
    "Literates - Scheduled Tribe - Persons"
]].copy()

df_india.columns = ["Class", "ST_Persons", "ST_Literate"]
df_india["ST_Illiterate"] = df_india["ST_Persons"] - df_india["ST_Literate"]

pivot = df_india.set_index("Class")

# Part 1: % ST living in Urban areas
st_total = float(pivot.loc["Total", "ST_Persons"])
st_urban = float(pivot.loc["Urban", "ST_Persons"])
urban_pct = (st_urban / st_total) * 100

print("Total ST (INDIA):", int(st_total))
print("Urban ST (INDIA):", int(st_urban))
print("% ST living in Urban areas:", round(urban_pct, 2), "%")

# Part 2: Pie chart (Urban ST literate vs illiterate)
urban_lit = float(pivot.loc["Urban", "ST_Literate"])
urban_illit = float(pivot.loc["Urban", "ST_Illiterate"])

plt.figure()
plt.pie([urban_lit, urban_illit],
        labels=["Literate ST (Urban)", "Illiterate ST (Urban)"],
        autopct="%1.1f%%")
plt.title("Scheduled Tribes in Urban Areas (INDIA, All Ages): Literate vs Illiterate")
plt.tight_layout()
plt.show()

import pandas as pd
import matplotlib.pyplot as plt

df = pd.read_csv("PCA_AY_2011_Revised.csv")

state_df = df[
    (df["District Code"] == 0) &
    (df["Area Name"] != "INDIA") &
    (df["Total/ Rural/ Urban"] == "Total") &
    (df["Adolescent and youth categories"] == "All Ages")
][[
    "Area Name", 
    "Total Population - Persons", 
    "Literates - Total - Persons"
]].copy()

state_df["IlliteratePersons"] = state_df["Total Population - Persons"] - state_df["Literates - Total - Persons"]
state_df["Literate_to_Illiterate_Ratio"] = state_df["Literates - Total - Persons"] / state_df["IlliteratePersons"]

# Sort by ratio for a clean comparison chart
state_df_sorted = state_df.sort_values("Literate_to_Illiterate_Ratio", ascending=False).reset_index(drop=True)

# Bar chart (state-wise ratios)
plt.figure(figsize=(16, 7))
x = range(len(state_df_sorted))
plt.bar(x, state_df_sorted["Literate_to_Illiterate_Ratio"])
plt.title("State/UT-wise Ratio of Literates to Illiterates (All Ages, Total)")
plt.xlabel("State / Union Territory (sorted by ratio)")
plt.ylabel("Literate : Illiterate (L/I) ratio")
plt.xticks(list(x), state_df_sorted["State/UT"], rotation=90)
plt.tight_layout()
plt.show()

# State-wise ratio of literates vs illiterates in all age groups (+ graph)

import pandas as pd
import matplotlib.pyplot as plt

# Step 1: Read dataset
df = pd.read_csv("PCA_AY_2011_Revised.csv")

# Step 2: Filter State/UT totals, Total, All Ages; exclude INDIA
state_df = df[
    (df["District Code"] == 0) &
    (df["Area Name"] != "INDIA") &
    (df["Total/ Rural/ Urban"] == "Total") &
    (df["Adolescent and youth categories"] == "All Ages")
][["Area Name", "Total Population - Persons", "Literates - Total - Persons"]].copy()

# Rename for ease
state_df = state_df.rename(columns={
    "Area Name": "State/UT",
    "Total Population - Persons": "TotalPersons",
    "Literates - Total - Persons": "LiteratePersons"
})

# Step 3: Compute Illiterates + Literate:Illiterate ratio
state_df["IlliteratePersons"] = state_df["TotalPersons"] - state_df["LiteratePersons"]
state_df["Literate_to_Illiterate_Ratio"] = state_df["LiteratePersons"] / state_df["IlliteratePersons"]

# Step 4: Sort for reporting + find highest/lowest
state_df_sorted = state_df.sort_values("Literate_to_Illiterate_Ratio", ascending=False).reset_index(drop=True)

highest = state_df_sorted.iloc[0]
lowest = state_df_sorted.iloc[-1]

print("Highest L:I ratio:", highest["State/UT"], round(highest["Literate_to_Illiterate_Ratio"], 3))
print("  Literates:", int(highest["LiteratePersons"]), "Illiterates:", int(highest["IlliteratePersons"]))

print("Lowest L:I ratio:", lowest["State/UT"], round(lowest["Literate_to_Illiterate_Ratio"], 3))
print("  Literates:", int(lowest["LiteratePersons"]), "Illiterates:", int(lowest["IlliteratePersons"]))

# Step 5: Graph (recommended for state-wise comparison)
plt.figure(figsize=(16, 7))
x = range(len(state_df_sorted))
plt.bar(x, state_df_sorted["Literate_to_Illiterate_Ratio"])
plt.title("State/UT-wise Ratio of Literates to Illiterates (All Ages, Total)")
plt.xlabel("State / Union Territory (sorted by ratio)")
plt.ylabel("Literate : Illiterate (L/I) ratio")
plt.xticks(list(x), state_df_sorted["State/UT"], rotation=90)
plt.tight_layout()
plt.show()

# (Optional) Save output for reuse
state_df_sorted.to_csv("task9_literate_vs_illiterate_ratio_statewise.csv", index=False)
print("Saved: task9_literate_vs_illiterate_ratio_statewise.csv")

import pandas as pd
        
df = pd.read_csv("PCA_AY_2011_Revised.csv")

st_df = df[
    (df["District Code"] == 0) &
    (df["Area Name"] != "INDIA") &
    (df["Total/ Rural/ Urban"] == "Total") &
    (df["Adolescent and youth categories"] == "All Ages")
][["Area Name", "Scheduled Tribe - Persons"]].copy()

st_df.columns = ["State/UT", "ST_Persons"]

st_sorted = st_df.sort_values("ST_Persons", ascending=False).reset_index(drop=True)

max_state = st_sorted.iloc[0]["State/UT"]
max_value = int(st_sorted.iloc[0]["ST_Persons"])

min_state = st_sorted.iloc[-1]["State/UT"]
min_value = int(st_sorted.iloc[-1]["ST_Persons"])

import pandas as pd

df = pd.read_csv("PCA_AY_2011_Revised.csv")

st_df = df[
    (df["District Code"] == 0) &
    (df["Area Name"] != "INDIA") &
    (df["Total/ Rural/ Urban"] == "Total") &
    (df["Adolescent and youth categories"] == "All Ages")
][["Area Name", "Scheduled Tribe - Persons"]].copy()

st_df.columns = ["State/UT", "ST_Persons"]

st_sorted = st_df.sort_values("ST_Persons", ascending=False).reset_index(drop=True)

max_state = st_sorted.iloc[0]["State/UT"]
max_value = int(st_sorted.iloc[0]["ST_Persons"])

min_state = st_sorted.iloc[-1]["State/UT"]
min_value = int(st_sorted.iloc[-1]["ST_Persons"])

print("Maximum ST:", max_state, max_value)
print("Minimum ST (including 0):", min_state, min_value)

# Optional: Minimum non-zero ST
nonzero = st_sorted[st_sorted["ST_Persons"] > 0]
if len(nonzero) > 0:
    min_nz_state = nonzero.iloc[-1]["State/UT"]
    min_nz_value = int(nonzero.iloc[-1]["ST_Persons"])
    print("Minimum ST (non-zero):", min_nz_state, min_nz_value)

import pandas as pd
import matplotlib.pyplot as plt

df = pd.read_csv("PCA_AY_2011_Revised.csv")

state_lit = df[
    (df["District Code"] == 0) &
    (df["Area Name"] != "INDIA") &
    (df["Total/ Rural/ Urban"] == "Total") &
    (df["Adolescent and youth categories"] == "All Ages")
][["Area Name", "Literates - Total - Males", "Literates - Total - Females"]].copy()

state_lit = state_lit.rename(columns={
    "Area Name": "State/UT",
    "Literates - Total - Males": "LiterateMales",
    "Literates - Total - Females": "LiterateFemales"
})

state_lit["Female_to_Male_Literate_Ratio"] = (
    state_lit["LiterateFemales"] / state_lit["LiterateMales"]
)

state_lit_sorted = state_lit.sort_values(
    "Female_to_Male_Literate_Ratio", ascending=False
).reset_index(drop=True)

plt.figure(figsize=(18, 7))
x = range(len(state_lit_sorted))
bar_width = 0.45

plt.bar([i - bar_width / 2 for i in x], state_lit_sorted["LiterateMales"],
        width=bar_width, label="Literate males")
plt.bar([i + bar_width / 2 for i in x], state_lit_sorted["LiterateFemales"],
        width=bar_width, label="Literate females")

plt.title("State/UT-wise Literates (All Ages, Total): Male vs Female")
plt.xlabel("State / Union Territory (sorted by Female/Male ratio)")
plt.ylabel("Number of literates (persons)")
plt.xticks(list(x), state_lit_sorted["State/UT"], rotation=90)
plt.legend()
plt.tight_layout()
plt.show()

import pandas as pd
import matplotlib.pyplot as plt

df = pd.read_csv("PCA_AY_2011_Revised.csv")

state_lit = df[
    (df["District Code"] == 0) &
    (df["Area Name"] != "INDIA") &
    (df["Total/ Rural/ Urban"] == "Total") &
    (df["Adolescent and youth categories"] == "All Ages")
][["Area Name", "Literates - Total - Males", "Literates - Total - Females"]].copy()

state_lit = state_lit.rename(columns={
    "Area Name": "State/UT",
    "Literates - Total - Males": "LiterateMales",
    "Literates - Total - Females": "LiterateFemales"
})

state_lit["Female_to_Male_Literate_Ratio"] = (
    state_lit["LiterateFemales"] / state_lit["LiterateMales"]
)

state_lit_sorted = state_lit.sort_values(
    "Female_to_Male_Literate_Ratio", ascending=False
).reset_index(drop=True)

highest = state_lit_sorted.iloc[0]
lowest = state_lit_sorted.iloc[-1]

print("Highest ratio:", highest["State/UT"],
      "Females:", int(highest["LiterateFemales"]),
      "Males:", int(highest["LiterateMales"]),
      "Ratio:", round(float(highest["Female_to_Male_Literate_Ratio"]), 4))

print("Lowest ratio:", lowest["State/UT"],
      "Females:", int(lowest["LiterateFemales"]),
      "Males:", int(lowest["LiterateMales"]),
      "Ratio:", round(float(lowest["Female_to_Male_Literate_Ratio"]), 4))

plt.figure(figsize=(18, 7))
x = range(len(state_lit_sorted))
bar_width = 0.45

plt.bar([i - bar_width / 2 for i in x], state_lit_sorted["LiterateMales"],
        width=bar_width, label="Literate males")
plt.bar([i + bar_width / 2 for i in x], state_lit_sorted["LiterateFemales"],
        width=bar_width, label="Literate females")

plt.title("State/UT-wise Literates (All Ages, Total): Male vs Female")
plt.xlabel("State / Union Territory (sorted by Female/Male ratio)")
plt.ylabel("Number of literates (persons)")
plt.xticks(list(x), state_lit_sorted["State/UT"], rotation=90)
plt.legend()
plt.tight_layout()
plt.show()

state_lit_sorted.to_csv("task11_statewise_literate_male_female.csv", index=False)
print("Saved: task11_statewise_literate_male_female.csv")