Greg Lamp glamp
glamp
/ pandasql_readme.py
Created
February 18, 2013 02:32
This file contains hidden or 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
| from sklearn.datasets import load_iris | |
| import pandas as pd | |
| from pandasql import sqldf | |
| import re | |
| iris = load_iris() | |
| iris_df = pd.DataFrame(iris.data, columns=iris.feature_names) | |
| iris_df['species'] = pd.Factor(iris.target, levels=iris.target_names) |
glamp
/ pandasql_plot_births_and_babies.py
Last active
April 2, 2018 12:52
This file contains hidden or 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 matplotlib.pyplot as plt | |
| from pandasql import * | |
| import pandas as pd | |
| pysqldf = lambda q: sqldf(q, globals()) | |
| q = """ | |
| SELECT | |
| m.date | |
| , m.beef |
glamp
/ logistic_load_data.py
Last active
December 14, 2015 10:39
This file contains hidden or 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 as pd | |
| import statsmodels.api as sm | |
| import pylab as pl | |
| import numpy as np | |
| # read the data in | |
| df = pd.read_csv("http://www.ats.ucla.edu/stat/data/binary.csv") | |
| # take a look at the dataset | |
| print df.head() |
glamp
/ logistic_looking_at_the_data.py
Last active
December 14, 2015 10:39
This file contains hidden or 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
| # summarize the data | |
| print df.describe() | |
| # admit gre gpa prestige | |
| # count 400.000000 400.000000 400.000000 400.00000 | |
| # mean 0.317500 587.700000 3.389900 2.48500 | |
| # std 0.466087 115.516536 0.380567 0.94446 | |
| # min 0.000000 220.000000 2.260000 1.00000 | |
| # 25% 0.000000 520.000000 3.130000 2.00000 | |
| # 50% 0.000000 580.000000 3.395000 2.00000 | |
| # 75% 1.000000 660.000000 3.670000 3.00000 |
glamp
/ logistic_prepping.py
Last active
December 14, 2015 10:39
This file contains hidden or 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
| # dummify rank | |
| dummy_ranks = pd.get_dummies(df['prestige'], prefix='prestige') | |
| print dummy_ranks.head() | |
| # prestige_1 prestige_2 prestige_3 prestige_4 | |
| # 0 0 0 1 0 | |
| # 1 0 0 1 0 | |
| # 2 1 0 0 0 | |
| # 3 0 0 0 1 | |
| # 4 0 0 0 1 |
glamp
/ logistic_do_regression.py
Last active
December 25, 2018 03:25
This file contains hidden or 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
| train_cols = data.columns[1:] | |
| # Index([gre, gpa, prestige_2, prestige_3, prestige_4], dtype=object) | |
| logit = sm.Logit(data['admit'], data[train_cols]) | |
| # fit the model | |
| result = logit.fit() |
glamp
/ logistic_results.py
Last active
December 14, 2015 10:39
This file contains hidden or 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
| # cool enough to deserve it's own gist | |
| print result.summary() |
glamp
/ logistic_conf_int.py
Last active
December 14, 2015 10:39
This file contains hidden or 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
| # look at the confidence interval of each coeffecient | |
| print result.conf_int() | |
| # 0 1 | |
| # gre 0.000120 0.004409 | |
| # gpa 0.153684 1.454391 | |
| # prestige_2 -1.295751 -0.055135 | |
| # prestige_3 -2.016992 -0.663416 | |
| # prestige_4 -2.370399 -0.732529 | |
| # intercept -6.224242 -1.755716 |
glamp
/ logistic_odds_ratio.py
Last active
December 14, 2015 10:39
This file contains hidden or 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
| # odds ratios only | |
| print np.exp(result.params) | |
| # gre 1.002267 | |
| # gpa 2.234545 | |
| # prestige_2 0.508931 | |
| # prestige_3 0.261792 | |
| # prestige_4 0.211938 | |
| # intercept 0.018500 |
glamp
/ logistic_ci_and_est.py
Last active
December 14, 2015 10:39
This file contains hidden or 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
| # odds ratios and 95% CI | |
| params = result.params | |
| conf = result.conf_int() | |
| conf['OR'] = params | |
| conf.columns = ['2.5%', '97.5%', 'OR'] | |
| print np.exp(conf) | |
| # 2.5% 97.5% OR | |
| # gre 1.000120 1.004418 1.002267 | |
| # gpa 1.166122 4.281877 2.234545 | |
| # prestige_2 0.273692 0.946358 0.508931 |