scratch.py

# Dependencies and Setup
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
import requests
import time
import os
import csv

#!!they will import a package incorrectly by misspelling it or by using the wrong alias


# Incorporated citipy to determine city based on latitude and longitude
from citipy import citipy

# Output File (CSV)
#output_data_file = 'output_data/cities.csv'
#!!They will export the CSV to the wrong folder name or use the wrong structure

# Range of latitudes and longitudes
lat_range = (-90, 90)
lng_range = (-180, 180)

# List for holding lat_lngs and cities
lat_lngs = []
cities = []

# Create a set of random lat and lng combinations
lats = np.random.uniform(low=-90.000, high=90.000, size=1500)
lngs = np.random.uniform(low=-180.000, high=180.000, size=1500)
lat_lngs = zip(lats, lngs)

# Identify nearest city for each lat, lng combination
for lat_lng in lat_lngs:
    city = citipy.nearest_city(lat_lng[0], lat_lng[1]).city_name

    # If the city is unique, then add it to a our cities list
    if city not in cities:
        cities.append(city)

# Print the city count to confirm sufficient count
len(cities)

# Starting URL for Weather Map API Call
url = 'http://api.openweathermap.org/data/2.5/weather?units=Imperial&APPID=' + '4429ca781d436624e4abcafd3849dd3d' #!!error in the api key due to extra space

# List for holding lat_lngs and cities
lat_lngs = []
cities = []

# Create a set of random lat and lng combinations
lats = np.random.uniform(low=-90.000, high=90.000, size=1500)
lngs = np.random.uniform(low=-180.000, high=180.000, size=1500)
lat_lngs = zip(lats, lngs)

# Identify nearest city for each lat, lng combination
for lat_lng in lat_lngs:
    city = citipy.nearest_city(lat_lng[0], lat_lng[1]).city_name

    # If the city is unique, then add it to a our cities list
    if city not in cities:
        cities.append(city)

# Print the city count to confirm sufficient count
(len(cities))

# Starting URL for Weather Map API Call
url = "http://api.openweathermap.org/data/2.5/weather?units=Imperial&APPID=" + "4429ca781d436624e4abcafd3849dd3d"

# List of city data
city_data = []

# Print to logger
print("Beginning Data Retrieval     ")
print("-----------------------------")

# Create counters
record_count = 1
set_count = 1

# Loop through all the cities in our list
for i, city in enumerate(cities):
    ##!!They will misform the for loop by not using the proper whitespace

    # Group cities in sets of 50 for logging purposes
    if (i % 50 == 0 and i >= 50):
        set_count += 1
        record_count = 0

    # Create endpoint URL with each city
    city_url = url + "&q=" + city

    # Log the url, record, and set numbers
    print("Processing Record %s of Set %s | %s" % (record_count, set_count, city))

    # Add 1 to the record count
    record_count += 1

    # Run an API request for each of the cities
    try:
        # Parse the JSON and retrieve data
        city_weather = requests.get(city_url).json()

        # Parse out the max temp, humidity, and cloudiness
        city_lat = city_weather["coord"]["lat"]
        city_lng = city_weather["coord"]["lon"]
        city_max_temp = city_weather["main"]["temp_max"]
        city_humidity = city_weather["main"]["humidity"]
        city_clouds = city_weather["clouds"]["all"]
        city_wind = city_weather["wind"]["speed"]
        city_country = city_weather["sys"]["country"]
        city_date = city_weather["dt"]

        # Append the City information into city_data list
        city_data.append({"City": city,
                          "Lat": city_lat,
                          "Lng": city_lng,
                          "Max Temp": city_max_temp,
                          "Humidity": city_humidity,
                          "Cloudiness": city_clouds,
                          "Wind Speed": city_wind,
                          "Country": city_country,
                          "Date": city_date})

    # If an error is experienced, skip the city
    except:
        print("City not found. Skipping...")
        pass

# Indicate that Data Loading is complete
print("-----------------------------")
print("Data Retrieval Complete      ")
print("-----------------------------")

# Convert array of JSONs into Pandas DataFrame
city_data_pd = pd.DataFrame(city_data)

# Extract relevant fields from the data frame
lats = city_data_pd["Lat"]
max_temps = city_data_pd["Max Temp"]
humidity = city_data_pd["Humidity"]
cloudiness = city_data_pd["Cloudiness"]
wind_speed = city_data_pd["Wind Speed"]

# Export the City_Data into a csv
#city_data_pd.to_csv(output_data_file, index_label="City_ID")

# Show Record Count
city_data_pd.count()

# Build scatter plot for latitude vs. temperature
plt.scatter(lats,
            max_temps,
            edgecolor="black", linewidths=1, marker="o",
            alpha=0.8, label="Cities")

# Incorporate the other graph properties
plt.title("City Latitude vs. Max Temperature (%s)" % time.strftime("%x"))
plt.ylabel("Max Temperature (F)")
plt.xlabel("Latitude")
plt.grid(True)

# Save the figure

direct = os.path.dirname(__file__)
filename = os.path.join(direct, "../Fig1.png")
plt.savefig(filename)

# Show plot
plt.show()

# Build the scatter plots for latitude vs. humidity
plt.scatter(lats,
            humidity,
            edgecolor="black", linewidths=1, marker="o",
            alpha=0.8, label="Cities")

# Incorporate the other graph properties
plt.title("City Latitude vs. Humidity (%s)" % time.strftime("%x"))
plt.ylabel("Humidity (%)")
plt.xlabel("Latitude")
plt.grid(True)

# Save the figure
filename2 = os.path.join(direct, "../Fig2.png")
plt.savefig(filename2)


# Show plot
plt.show()