DataSkills/assignment_1_final.py at master · awastro55/DataSkills · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Mon Oct 14 22:42:34 2019

@author: andrewweis
"""

#Data Skills for Public Policy Pset1.  Reorganizing code.

#Import packages
import os
import us
import pandas as pd
import requests
from bs4 import BeautifulSoup
import matplotlib.pyplot as plt

#Webscraping function to create our csv files
def get_webpage(urls, filepath, data=None, headers=None, return_soup=True):
    for url in urls:
        if data:
            response=requests.post(url, data=data)
        else:
            response=requests.get(url)
        soup=BeautifulSoup(response.text)
        state, measure, month = response.text.split('\n')[0].split(', ')

        with open(os.path.join(filepath, state+'_'+month+'.csv'), 'w') as ofile:
            ofile.write(response.text)
    if return_soup:
        return soup
    else:
        return response

#Function to create data frame
def create_df(filepath, skiprows=0):
    dfs=[]
    files=os.listdir(filepath)
    for f in files:
        #print('f=',f)
        state, month = f.split('_')
        if f=='.DS_Store':
            continue
        df = pd.read_csv(os.path.join(filepath, f), skiprows=skiprows)
        df['State'] = state
        #print(state)
        df['Date'] = pd.to_datetime(df['Date'], format='%Y%m')
        dfs.append(df)
    df=pd.concat(dfs)
    df=df.sort_values(['State', 'Date'])

    return df

#Plotting function--temperature difference plot
def plotdiff(filepath_plotdiff,df,states):
    df['Year'] = df['Date'].map(lambda d: d.year)
    #print(df['Year'])
    df['Jan-Aug Delta'] = df.groupby(['State', 'Year'])['Value'].diff()
    df_delta = df.dropna(subset=['Jan-Aug Delta'])[['State', 'Year', 'Jan-Aug Delta']]
    #print(df_delta)

    fig, ax = plt.subplots(len(states), 1)
    il = df_delta[df_delta['State'] == states[0]]
    ax[0].plot(il['Year'], il['Jan-Aug Delta'], 'k-')
    ax[0].set_ylabel('Illinois')
    ax[0].xaxis.tick_top()

    ca = df_delta[df_delta['State'] == states[1]]
    #print(ca)
    ax[1].plot(ca['Year'], ca['Jan-Aug Delta'], 'r-')
    ax[1].set_ylabel('California')
    ax[1].set_label('')
    ax[1].set_xticks([])
    ax[1].xaxis.set_ticks_position('none')

    ny = df_delta[df_delta['State'] == states[2]]
    ax[2].plot(ny['Year'], ny['Jan-Aug Delta'], 'b-')
    ax[2].set_ylabel('New York')
    ax[2].set_label('')
    ax[2].set_xticks([])
    ax[2].xaxis.set_ticks_position('none')

    tx = df_delta[df_delta['State'] == states[3]]
    ax[3].plot(tx['Year'], tx['Jan-Aug Delta'], 'g-')
    ax[3].set_ylabel('Texas')

    plt.suptitle('Average Jan-Aug Temperature Variation')
    plt.savefig(filepath_plotdiff)
    plt.show()

def plotmonth(filepath_plotmonth,df,states):
    df['Month'] = df['Date'].map(lambda d: d.month)
    df_aug = df[df['Month'] == 8]

    fig, ax = plt.subplots(1, 1)
    il = df_aug[df_aug['State'] == states[0]]
    ca = df_aug[df_aug['State'] == states[1]]
    ny = df_aug[df_aug['State'] == states[2]]
    tx = df_aug[df_aug['State'] == states[3]]

    print('Max/Mean/Min for Illinois:', il['Value'].max(), il['Value'].mean(), il['Value'].min())
    print('Max/Mean/Min for California:', ca['Value'].max(), ca['Value'].mean(), ca['Value'].min())
    print('Max/Mean/Min for New York:', ny['Value'].max(), ny['Value'].mean(), ny['Value'].min())
    print('Max/Mean/Min for Texas:', tx['Value'].max(), tx['Value'].mean(), tx['Value'].min())

    ax.plot(il['Year'], il['Value'], 'k-', label=states[0])
    ax.plot(ca['Year'], ca['Value'], 'r-', label='California')
    ax.plot(ny['Year'], ny['Value'], 'b-', label='New York')
    ax.plot(tx['Year'], tx['Value'], 'g-', label='Texas')
    ax.legend(loc='upper right')
    plt.suptitle('Average August Temperature')
    plt.savefig(filepath_plotmonth)
    plt.show()

#Get the urls
urls=[]
head_url='https://www.ncdc.noaa.gov/cag/statewide/time-series/'
tail_url = '-1895-2019.csv?base_prd=true&begbaseyear=1901&endbaseyear=2000'
for state in range(1,49):
    for month in [1,8]:
        urls.append(head_url+str(state)+'-tavg-1-'+str(month)+tail_url)

#States to plot
states=['Illinois','California', 'New York', 'Texas']
def main(urls, states, filepath, filepath_plotdiff, filepath_plotmonth, data=None, headers=None,
         return_soup=True, skiprows=0):
    get_webpage(urls, filepath, data=None, headers=None, return_soup=True)
    df=create_df(filepath, skiprows=skiprows)
    plotdiff(filepath_plotdiff,df,states)
    plotmonth(filepath_plotmonth,df,states)

main(urls, states, '/Users/andrewweis/Documents/GitHub/DataSkills/Pset1/weather/',
     '/Users/andrewweis/Documents/GitHub/DataSkills/Pset1/weather_plots/JanAugDiff.png',
     '/Users/andrewweis/Documents/GitHub/DataSkills/Pset1/weather_plots/Aug.png', skiprows=4)