data science #2

Who is John Snow and what is he known for?

Pioneer of data mapping; used a cholera map to trace disease to a water pump.

What are common sources of data?

Transactions, sensors, social media, surveys, observational studies.

What is the main goal of data science?

Extract insights from data using stats, programming, and domain knowledge.

What are the 5 C's of data ethics?

Consent, Clarity, Control, Consequences, Consistency.

What is the key idea in "The Signal and the Noise" (Ch. 1)?

Focus on identifying real patterns (signals) vs. random noise in data.

What does len("hello") return?

5

What does "Age: %d" % 25 output?

"Age: 25"

What does [1, 2, 3, 4][2:4] return?

[3, 4]

What does type(3.14) return?

float

What is the output of max([3, 9, 1])?

9

What does np.argmin([10, 5, 8]) return?

1 (index of smallest value)

What is a condition variable in NumPy?

A boolean array used to filter values, e.g., arr > 5.

What does arr[cv] do?

Returns values in arr where condition cv is True.

How do you load a CSV into a dataframe?

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

How do you access a column named "Age"?

df["Age"]

How do you filter out NaN values in a column?

pd.notna(df["colName"])

How do you make a histogram using Matplotlib?

plt.hist(numbers, bins=10)

How do you make a barplot with Seaborn?

sns.barplot(x="col1", y="col2", data=df)

What does sns.heatmap(df.corr(), annot=True) do?

Displays a heatmap of correlations with annotations.

What does model.fit(X, y) do?

Trains a linear regression model on data.

How do you get the slope and intercept?

model.coef_ and model.intercept_

How do you make a prediction with x = 5?

model.predict([[5]])

What’s the key idea of "Prediction Machines"?

Machine learning reduces prediction cost, changing decision-making.

What are three types of machine learning?

Supervised, Unsupervised, Reinforcement.

What’s overfitting in machine learning?

When a model fits training data too closely and fails on new data.