# 1 - Import necessary libraries import os, random import pandas as pd import numpy as np import matplotlib.pyplot as plt

# 2 - Retrieve the names of the 22 files and assign them to a List variable # You would need to filter out other files # Display the names of these 22 files Files= os.listdir('CollegeScorecard_Raw_Data') Files

# 3 - Write code to randomly select one file name out of the 22 files names. # Hint: generate a random integer between 0 and 21 first # Display the file name random_file=random.choice(os.listdir("CollegeScorecard_Raw_Data")) print ("File Name:",random_file)

# 4 - Only read the two columns: college name (INSTNM) and in state tution ("TUITIONFEE_IN") # from this file into a data frame aand display use info() function to display a summary information df = pd.read_csv(random_file,index_col=None, header=0, usecols=["INSTNM","TUITIONFEE_IN"]) df

# 5 - Find out how many observations have missing value. print(" \nCount total NaN at each column in a DataFrame : \n\n", df.isnull().sum())

# 6 - Drop those observations with missing value # Disaply the number of observations afterward df["TUITIONFEE_IN"] = df["TUITIONFEE_IN"].fillna(0) print(" \nCount total NaN at each column in a DataFrame : \n\n", df.isnull().sum())

# 7 - Find out how many observations have 0 tution. df[df["TUITIONFEE_IN"]== 0]

# 8 - Drop those observations with 0 tuition # Disaply the number of observations afterward df= df[df['TUITIONFEE_IN'] != 0] df

# 9 - Calculate and display the mean (average) of the tuitions of all the remaining observations df.describe()

# 10 - Randomly select just 1 observation from the data frame. # Display the tuition of that observation. dfr= df.sample() dfr

# 11 - Calculate the different between the tuition of this observation and # the mean tuition off all observations calculated earlier. # Display the difference TF1= dfr["TUITIONFEE_IN"] Diff= TF1-(df["TUITIONFEE_IN"].mean()) Diff

# 12 - Repeat 10 to 11 several times get the feel of the size of the difference in means dfr1= df.sample() TF2= dfr1["TUITIONFEE_IN"] Diff= TF2-(df["TUITIONFEE_IN"].mean()) Diff

dfr2= df.sample() TF3= dfr2["TUITIONFEE_IN"] Diff= TF3-(df["TUITIONFEE_IN"].mean()) Diff

dfr3= df.sample() TF4= dfr3["TUITIONFEE_IN"] Diff= TF4-(df["TUITIONFEE_IN"].mean()) Diff

dfr4= df.sample() TF5= dfr4["TUITIONFEE_IN"] Diff= TF5-(df["TUITIONFEE_IN"].mean()) Diff

# 13 - Randomly select 20 observations, display the tuition of these observation. dfr20= df.sample(20) dfr20

# 14 - Calculate and displat the mean tuition of these 20 observations df_mean20= dfr20["TUITIONFEE_IN"].mean() df_mean20

# 15 - Calculate the different between the average tuition of these 20 observations # and the mean tuition off all observations calculated earlier. # Display the difference Diff2= df_mean20 -(df["TUITIONFEE_IN"].mean()) Diff2

# 16 - Repeat 13 to 15 several times and get the feel of the size of the difference in means # Compare these differences with the differences calculated earlier with just 1 observation # Describe your hunch/conclusion

dfr20= df.sample(20) df_mean20= dfr20["TUITIONFEE_IN"].mean() Diff3= df_mean20 -(df["TUITIONFEE_IN"].mean()) Diff3

dfr20= df.sample(20) df_mean20= dfr20["TUITIONFEE_IN"].mean() Diff4= df_mean20 -(df["TUITIONFEE_IN"].mean()) Diff4

dfr20= df.sample(20) df_mean20= dfr20["TUITIONFEE_IN"].mean() Diff5= df_mean20 -(df["TUITIONFEE_IN"].mean()) Diff5

# 17 - write function Code here DIFFM is the mean difference using two variables X and Y def DiffM (x,y): df_x=y.sample(x) mean_x=df_x["TUITIONFEE_IN"].mean() df_mean=df["TUITIONFEE_IN"].mean() return mean_x-df_mean

# 18 - test the function by passing a sample size and the name of the dataframe # Dsplay the return of the function Use sample size 10 and the orgiginal data frame to find the differnce in means DiffM(10,df)

# 19 - Create a list of sequence numbers from 1 to 50, name it "sample_sizes"; # display it to make sure its members are from 1 to 50 sample_sizes= list(range(1, 51)) print(sample_sizes)

# 20 - Create an empty list and name it "means_diff" for differences of population mean and sample means; # Loop through the list sample_sizes: # For each element in the sample size list, obtain a random sample of that size from the data frame; # Calculate the sample mean # Calculate the difference between the population mean and the sample mean # Append the difference to the list "means_diff" # Display the list "means_diff" after the loop is completed means_diff=[] for num in sample_sizes: df_num= df.sample(num) mean_num=df_num['TUITIONFEE_IN'].mean() difference=mean_num-(df["TUITIONFEE_IN"].mean()) means_diff.append(difference) print(means_diff)

# 21 - Make a scatter plot with sample size on the x-axs and mean difference on the y-axis # Observe as the sample size increases, the sample means converge to the population mean. # Make sure you make the plot large enough plt.scatter(sample_sizes,means_diff,plt.gcf().set_size_inches(15, 8)) plt.xlabel('Sample size') plt.ylabel('Mean difference') plt.title('Sample Size V.S. Differences in Means') plt.show()

# 22 - repeat 18 to 21 by replacing 50 with a larger number. For example, 300, or even 1000. # and see how the plot looks. sample_sizes2= list(range(1, 301)) print(sample_sizes2)

means_diff=[] for num in sample_sizes2: df_num= df.sample(num) mean_num=df_num['TUITIONFEE_IN'].mean() difference=mean_num-(df["TUITIONFEE_IN"].mean()) means_diff.append(difference) print(means_diff)

plt.scatter(sample_sizes2,means_diff,plt.gcf().set_size_inches(15, 8)) plt.xlabel('Sample size') plt.ylabel('Mean difference') plt.title('Sample Size V.S. Differences in Means') plt.show()