Skip to content

Title goes here

Photo by Jannis Lucas on Unsplash.

Every year, American high school students take SATs, which are standardized tests intended to measure literacy, numeracy, and writing skills. There are three sections - reading, math, and writing, each with a maximum score of 800 points. These tests are extremely important for students and colleges, as they play a pivotal role in the admissions process.

Analyzing the performance of schools is important for a variety of stakeholders, including policy and education professionals, researchers, government, and even parents considering which school their children should attend.

You have been provided with a dataset called schools.csv, which is previewed below.

You have been tasked with answering three key questions about New York City (NYC) public school SAT performance.

# Re-run this cell 
import pandas as pd

# Read in the data
schools = pd.read_csv("schools.csv")

# Preview the data
schools.head()

# Start coding here...
# Add as many cells as you like...
import pandas as pd

# Load the dataset
schools = pd.read_csv("schools.csv")

# Calculate standard deviation across SAT sections for each school
schools["std_dev"] = schools[["average_math", "average_reading", "average_writing"]].std(axis=1)

# Find the school with the largest standard deviation and keep it as a DataFrame
largest_std_dev = schools.loc[[schools["std_dev"].idxmax()]]

# Display the result
print(largest_std_dev)
import pandas as pd

# Load the dataset
schools = pd.read_csv("schools.csv")

# Calculate standard deviation across SAT sections for each school
schools["std_dev"] = schools[["average_math", "average_reading", "average_writing"]].std(axis=1)

# Get the total number of schools
num_schools = schools.shape[0]

# Get the row with the largest std deviation, as a DataFrame
largest_std_dev = schools.loc[[schools["std_dev"].idxmax()]]

# Add the num_schools column
largest_std_dev["num_schools"] = num_schools

# Display the result
print(largest_std_dev)
import pandas as pd

# Load the dataset
schools = pd.read_csv("schools.csv")

# Calculate std deviation across SAT sections
schools["std_dev"] = schools[["average_math", "average_reading", "average_writing"]].std(axis=1)

# Calculate average SAT score across sections
schools["average_SAT"] = schools[["average_math", "average_reading", "average_writing"]].mean(axis=1)

# Get total number of schools
num_schools = schools.shape[0]

# Get the row with the largest std deviation as a DataFrame
largest_std_dev = schools.loc[[schools["std_dev"].idxmax()]]

# Add num_schools column
largest_std_dev["num_schools"] = num_schools

# Display the final result
print(largest_std_dev)
import pandas as pd

# Load the dataset
schools = pd.read_csv("schools.csv")

# Calculate average and standard deviation across SAT sections
schools["average_SAT"] = schools[["average_math", "average_reading", "average_writing"]].mean(axis=1)
schools["std_SAT"] = schools[["average_math", "average_reading", "average_writing"]].std(axis=1)

# Get total number of schools
num_schools = schools.shape[0]

# Get the row with the highest std_SAT as a DataFrame
largest_std_dev = schools.loc[[schools["std_SAT"].idxmax()]]

# Add num_schools column
largest_std_dev["num_schools"] = num_schools

# Display the result
print(largest_std_dev)
import pandas as pd

# Load dataset
schools = pd.read_csv("schools.csv")

# Step 1: Create total_SAT = sum of the 3 section scores
schools["total_SAT"] = schools["average_math"] + schools["average_reading"] + schools["average_writing"]

# Step 2: Group by borough and calculate std deviation of total_SAT
borough_std = schools.groupby("borough")["total_SAT"].std()

# Step 3: Get the borough with the largest std deviation
largest_std_borough = borough_std.idxmax()
largest_std_value = borough_std.max()

# Step 4: Optional — create a DataFrame to display clearly
largest_std_dev_borough = pd.DataFrame({
    "borough": [largest_std_borough],
    "std_total_SAT": [largest_std_value]
})

# Display the result
print(largest_std_dev_borough)
# Re-run this cell 
import pandas as pd

# Read in the data
schools = pd.read_csv("schools.csv")

# Preview the data
schools.head()

# Start coding here...

# Which schools are best for math?
best_math_schools = schools[schools["average_math"] >= 640][["school_name", "average_math"]].sort_values("average_math", ascending=False)

# Calculate total_SAT per school
schools["total_SAT"] = schools["average_math"] + schools["average_reading"] + schools["average_writing"]

# Who are the top 10 performing schools?
top_10_schools = schools.sort_values("total_SAT", ascending=False)[["school_name", "total_SAT"]].head(10)

# Which NYC borough has the highest standard deviation for total_SAT?
boroughs = schools.groupby("borough")["total_SAT"].agg(["count", "mean", "std"]).round(2)

# Filter for max std and make borough a column
largest_std_dev = boroughs[boroughs["std"] == boroughs["std"].max()]

# Rename the columns for clarity
largest_std_dev = largest_std_dev.rename(columns={"count": "num_schools", "mean": "average_SAT", "std": "std_SAT"})

# Optional: Move borough from index to column
largest_std_dev.reset_index(inplace=True)