Uniform distribution in SciPy - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is a uniform distribution?

A uniform distribution is a type of probability distribution where all outcomes are equally likely within a certain range. It means every value between the minimum and maximum has the same chance of occurring.

beginner

How do you create a uniform distribution in scipy?

You use scipy.stats.uniform and specify the loc (start) and scale (width) parameters. For example, uniform(loc=0, scale=1) creates a uniform distribution from 0 to 1.

beginner

What does the pdf function do in a uniform distribution?

The pdf (probability density function) gives the height of the distribution at a specific point. For uniform distribution, it is constant between the start and end, showing equal likelihood.

beginner

How do you generate random numbers from a uniform distribution using scipy?

Use the rvs() method from a uniform distribution object. For example, uniform(loc=0, scale=10).rvs(size=5) generates 5 random numbers between 0 and 10.

beginner

What are the parameters loc and scale in scipy's uniform distribution?

loc is the starting point (minimum value) of the distribution. scale is the length of the interval (max - min). The distribution covers values from loc to loc + scale.

What is the shape of the probability density function (pdf) for a uniform distribution?

A A rising slope

B A bell curve

C A U shape

D A flat horizontal line

The pdf of a uniform distribution is flat because all values in the range are equally likely.

In scipy, which parameter sets the minimum value of a uniform distribution?

A loc

B scale

C size

D shape

loc sets the starting point (minimum) of the uniform distribution.

How do you generate 10 random samples from a uniform distribution between 5 and 15 using scipy?

A uniform(loc=5, scale=10).rvs(size=10)

B uniform(loc=0, scale=10).rvs(size=5)

C uniform(loc=5, scale=15).rvs(size=10)

D uniform(loc=10, scale=5).rvs(size=10)

The distribution starts at 5 with a scale of 10, so it covers 5 to 15. rvs(size=10) generates 10 samples.

What does the pdf value represent in a uniform distribution?

A The probability of a single exact value

B The mean of the distribution

C The height of the distribution at a point

D The cumulative probability up to a point

The pdf gives the height of the distribution curve at a specific value.

If a uniform distribution has loc=2 and scale=3, what is the range of values it covers?

A 0 to 3

B 2 to 5

C 3 to 5

D 2 to 3

The range is from loc (2) to loc + scale (2 + 3 = 5).

Explain how to create and use a uniform distribution in scipy to generate random numbers.

Think about setting the start and length of the distribution, then drawing samples.

Describe what the probability density function (pdf) of a uniform distribution looks like and what it means.

Imagine a straight line showing equal chance for all values in the range.

Practice

1. What does the loc parameter represent in the scipy.stats.uniform distribution?

easy

A. The starting point (minimum value) of the uniform distribution range

B. The width (length) of the uniform distribution range

C. The mean of the uniform distribution

D. The variance of the uniform distribution

Solution

1. Step 1: Understand the parameters of uniform distribution

   The uniform distribution in scipy uses loc as the starting point of the range and scale as the length of the range.

2. Step 2: Identify the role of loc

   The loc parameter sets the minimum value where the uniform distribution starts.

3. Final Answer:

   The starting point (minimum value) of the uniform distribution range -> Option A

4. Quick Check:

   loc = start value [OK]

Hint: Remember: loc = start, scale = length [OK]

Common Mistakes:

• Confusing loc with scale
• Thinking loc is the mean
• Mixing loc with variance

2. Which of the following is the correct way to create a uniform distribution from 5 to 15 using scipy?

easy

A. uniform(loc=10, scale=5)

B. uniform(loc=5, scale=15)

C. uniform(loc=5, scale=10)

D. uniform(loc=0, scale=10)

Solution

1. Step 1: Calculate scale from range

   The range is from 5 to 15, so the length is 15 - 5 = 10. This is the scale.

2. Step 2: Set loc and scale correctly

   Set loc=5 (start) and scale=10 (length) to cover 5 to 15.

3. Final Answer:

   uniform(loc=5, scale=10) -> Option C

4. Quick Check:

   loc=5, scale=15-5=10 [OK]

Hint: Scale = end - start, loc = start [OK]

Common Mistakes:

• Swapping loc and scale values
• Using scale as the end value
• Setting loc to zero incorrectly

3. What is the output of this code?

from scipy.stats import uniform
rv = uniform(loc=2, scale=3)
print(round(rv.pdf(3), 2))

medium

A. 0.33

B. 0.20

C. 0.50

D. 0.00

Solution

1. Step 1: Understand PDF of uniform distribution

   PDF is constant inside the range and equals 1/scale. Here, scale=3, so PDF = 1/3 ≈ 0.3333.

2. Step 2: Check if x=3 is inside the range

   Range is from loc=2 to 2+3=5. Since 3 is inside, PDF at 3 is 1/3 ≈ 0.33.

3. Final Answer:

   0.33 -> Option A

4. Quick Check:

   PDF = 1/scale = 1/3 = 0.33 [OK]

Hint: PDF inside range = 1/scale [OK]

Common Mistakes:

• Calculating PDF as zero inside range
• Using loc instead of scale for PDF
• Rounding errors without checking range

4. Identify the error in this code snippet:

from scipy.stats import uniform
rv = uniform(loc=1, scale=4)
prob = rv.cdf(6)
print(prob)

medium

A. The scale should be 5 to cover up to 6

B. No error; code runs correctly

C. The loc parameter must be zero

D. The cdf method does not exist for uniform

Solution

1. Step 1: Check parameters and range

   loc=1 and scale=4 means range is from 1 to 5 (1+4=5).

2. Step 2: Evaluate cdf at 6

   6 is outside the range (greater than 5), so cdf(6) should return 1 (full probability).

3. Step 3: Confirm method existence and output

   The cdf method exists for uniform and returns valid output even outside range.

4. Final Answer:

   No error; code runs correctly -> Option B

5. Quick Check:

   cdf exists and returns 1 for x > loc+scale [OK]

Hint: CDF returns 1 for x beyond range max [OK]

Common Mistakes:

• Thinking scale must cover queried x
• Assuming cdf method is missing
• Believing loc must be zero

5. You want to model a uniform distribution for daily temperatures between 10°C and 20°C. Which code correctly calculates the probability that temperature is less than 15°C?

hard

A. rv = uniform(loc=10, scale=5)
prob = rv.cdf(15)

B. rv = uniform(loc=10, scale=20)
prob = rv.cdf(15)

C. rv = uniform(loc=0, scale=10)
prob = rv.cdf(15)

D. rv = uniform(loc=10, scale=10)
prob = rv.cdf(15)

Solution

1. Step 1: Set correct loc and scale for temperature range

   Range is 10 to 20, so loc=10 and scale=20-10=10.

2. Step 2: Calculate CDF at 15

   CDF at 15 is (15 - loc)/scale = (15-10)/10 = 0.5, which is the probability temperature is less than 15.

3. Final Answer:

   rv = uniform(loc=10, scale=10) prob = rv.cdf(15) -> Option D

4. Quick Check:

   prob = (15-10)/10 = 0.5 [OK]

Hint: CDF = (x - loc) / scale inside range [OK]

Common Mistakes:

• Using wrong scale length
• Setting loc to zero incorrectly
• Calculating CDF outside range without adjustment