Created
February 9, 2016 05:09
-
-
Save tpatch/a44e78410ed29ca4e68b to your computer and use it in GitHub Desktop.
For online data visualization course
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import pandas | |
import numpy | |
pandas.set_option('display.float_format', lambda x: '%f'%x) | |
data = pandas.read_csv('datasets/ool_pds.csv', low_memory=False) | |
data.columns = map(str.upper, data.columns) | |
print(len(data)) | |
print(len(data.columns)) | |
data["W1_A11"] = data["W1_A11"].convert_objects(convert_numeric=True) | |
data["W1_K1_B"] = data["W1_K1_B"].convert_objects(convert_numeric=True) | |
data["W1_K1_A"] = data["W1_K1_A"].convert_objects(convert_numeric=True) | |
data["W1_K1_C"] = data["W1_K1_C"].convert_objects(convert_numeric=True) | |
data["W1_K1_D"] = data["W1_K1_D"].convert_objects(convert_numeric=True) | |
data["W1_B4"] = data["W1_B4"].convert_objects(convert_numeric=True) | |
# Pull and print variables | |
recode1 = {1:0, 2:1, 3:2, 4:3, 5:4, 6:5, 7:6, 8:7} | |
print("Days of week Watching News") | |
# news = data["W1_A11"].value_counts(sort=True, normalize=True) | |
data["W1_A11"] = data["W1_A11"].replace(-1, numpy.nan) | |
c1 = data["W1_A11"].map(recode1) | |
news = c1.value_counts(sort=True, normalize=True, ascending=True, dropna=True) | |
print(news) | |
# Break tv watching days into groups | |
recodeFreq = {"(0, 2]": "0-1 Days", "(2, 4]": "2-3 Days", "(4, 6]": "4-5 Days", "(6, 8]": "6-7 Days"} | |
data["TVDAYSFREQ"] = pandas.cut(data.W1_A11, [0, 2, 4, 6, 8]) | |
c1b = data["TVDAYSFREQ"].map(recodeFreq) | |
daysFreq = c1b.value_counts(normalize=True, dropna=True, sort=True, ascending=True) | |
print("Days of week Watching News - Binned") | |
print(daysFreq) | |
recode2 = {1: "Just About Always", 2: "Most of the Time", 3: "Only Some of the Time", 4: "Never"} | |
print("How much do you think you can trust the police?") | |
data["W1_K1_B"] = data["W1_K1_B"].replace(-1, numpy.nan) | |
c2 = data["W1_K1_B"].map(recode2) | |
police = c2.value_counts(sort=True, normalize=True, ascending=True, dropna=True) | |
print(police) | |
print("How much do you think you can trust the government?") | |
data["W1_K1_A"] = data["W1_K1_A"].replace(-1, numpy.nan) | |
c3 = data["W1_K1_A"].map(recode2) | |
govt = c3.value_counts(sort=True, normalize=True, ascending=True, dropna=True) | |
print(govt) | |
print("How much do you think you can trust the Legal System?") | |
data["W1_K1_C"] = data["W1_K1_C"].replace(-1, numpy.nan) | |
c4 = data["W1_K1_C"].map(recode2) | |
lsystem = c4.value_counts(sort=True, normalize=True, ascending=True, dropna=True) | |
print(lsystem) | |
print("How much do you think you can trust the Public Schools?") | |
data["W1_K1_D"] = data["W1_K1_D"].replace(-1, numpy.nan) | |
c5 = data["W1_K1_D"].map(recode2) | |
pschool = c5.value_counts(sort=True, normalize=True, ascending=True, dropna=True) | |
print(pschool) | |
recodeAnger = {1: "Extremely Angry", 2: "Very Angry", 3: "Somewhat Angry", 4: "A Little Angry", 5: "Not Angry at All"} | |
print("Generally speaking, how angry do you feel about the way things are going in the country these days?") | |
data["W1_B4"] = data["W1_B4"].replace(-1, numpy.nan) | |
c6 = data["W1_B4"].map(recodeAnger) | |
anger = c6.value_counts(sort=True, normalize=True, ascending=True, dropna=True) | |
print(anger) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment