Statistics and Linear Algebra 6

1. Two ways to get a column of another column with max/min values:

　　a. most_bars_country = flags["name"][flags["bars"].idxmax()]

　　b. bars_sorted = flags.sort_values("bars", ascending=[0])

　　　　most_bars_country = bars_sorted["name"].iloc[0]

2. The way to get the probability of a certain value in a column:

　　orange_probability = flags[flags["orange"]==1].shape[0]/flags.shape[0]

3. The way to calculate combination by using factorial：　

　　import math
　　def find_outcome_combinations(N, k): # Calculate the numerator of our formula.
　　　　numerator = math.factorial(N) # Calculate the denominator.
　　　　denominator = math.factorial(k) * math.factorial(N - k) # Divide them to get the final value.
　　　　return numerator / denominator

4. The easier way to calculate the prabability of a number in a combination by using a library of scipy:

　　import scipy
　　from scipy import linspace
　　from scipy.stats import binom

　　outcome_counts = linspace(0,30,31) # Create a range of numbers from 0 to 30, with 31 elements (each number has one entry).
　　dist = binom.pmf(outcome_counts,30,0.39) # The list of probability of the combination. 
　　plt.bar(outcome_counts,dist)
　　plt.show()

　

5. Sometimes we'll want to be able to tell people the expected value of a probability distribution -- the most likely result of a single sample that we look at.? To compute this, we just multiply N by p.

6. If we would like to calculate the probability of value k or less will occur, we can use cummulate density function:

　　outcome_counts = linspace(0,30,31)

　　dist = binom.cdf(outcome_counts,30,0.39) #To get cummulate density 

　　plt.plot(outcome_counts,dist)

7.

转载于:https://www.cnblogs.com/kingoscar/p/6143510.html