Completed assignment_07 PR

analytics.py

@@ -0,0 +1,176 @@
+from point import Point
+import math
+import statistics
+import random
+
+def mean_center(points):
+    """
+    Given a set of points, compute the mean center
+
+    Parameters
+    ----------
+    points : list
+         A list of points in the form (x,y)
+
+    Returns
+    -------
+    x : float
+        Mean x coordinate
+
+    y : float
+        Mean y coordinate
+    """
+    total = len(points)
+    y = 0
+    x = 0
+    for point in points:
+        x += point[0]
+        y += point[1]
+
+    x = x/total
+    y = y/total
+    return x, y
+
+def minimum_bounding_rectangle(points):
+    """
+    Given a set of points, compute the minimum bounding rectangle.
+
+    Parameters
+    ----------
+    points : list
+             A list of points in the form (x,y)
+
+    Returns
+    -------
+     : list
+       Corners of the MBR in the form [xmin, ymin, xmax, ymax]
+    """
+    x_list = []
+    y_list = []
+
+    for p in points:
+        x_list.append(p[0])
+        y_list.append(p[1])
+
+    mbr = [0,0,0,0]
+    mbr[0] = min(x_list)
+    mbr[1] = min(y_list)
+    mbr[2] = max(x_list)
+    mbr[3] = max(y_list)
+
+    return mbr
+
+
+def mbr_area(mbr):
+    """
+    Compute the area of a minimum bounding rectangle
+    """
+    width = mbr[2] - mbr[0]
+    length = mbr[3] - mbr[1]
+    area = width * length
+
+    return area
+
+
+def expected_distance(area, n):
+    """
+    Compute the expected mean distance given
+    some study area.
+
+    This makes lots of assumptions and is not
+    necessarily how you would want to compute
+    this.  This is just an example of the full
+    analysis pipe, e.g. compute the mean distance
+    and the expected mean distance.
+
+    Parameters
+    ----------
+    area : float
+           The area of the study area
+
+    n : int
+        The number of points
+    """
+
+    expected = 0.5 * (math.sqrt( area / n ))
+    return expected
+
+
+"""
+Below are the functions that you created last week.
+Your syntax might have been different (which is awesome),
+but the functionality is identical.  No need to touch
+these unless you are interested in another way of solving
+the assignment
+"""
+
+def manhattan_distance(a, b):
+    """
+    Compute the Manhattan distance between two points
+
+    Parameters
+    ----------
+    a : tuple
+        A point in the form (x,y)
+
+    b : tuple
+        A point in the form (x,y)
+
+    Returns
+    -------
+    distance : float
+               The Manhattan distance between the two points
+    """
+    distance =  abs(a[0] - b[0]) + abs(a[1] - b[1])
+    return distance
+def create_random_marked_points(n, marks = None):
+    point_list = []
+    rand = random.Random()
+    for i in range(n):
+        rand_x = round(rand.uniform(0,1),2)
+        rand_y = round(rand.uniform(0,1),2)
+        if marks is None:
+            point_list.append(Point(rand_x, rand_y))
+        else:
+            rand_mark = random.choice(marks)
+            point_list.append(Point(rand_x, rand_y, rand_mark))
+    return point_list
+
+def euclidean_distance(a, b):
+    distance = math.sqrt((a.x - b.x)**2 + (a.y - b.y)**2)
+    return distance
+
+def average_nearest_neighbor_distance(points, mark = None):
+    new_points = []
+    if mark is None:
+        new_points = points
+    else:
+        for point in points:
+            if point.mark is mark:
+                new_points.append(point)
+
+    dists = []
+    for num1, point in enumerate(new_points):
+        dists.append(None) 
+        for num2, point2 in enumerate(new_points):
+            if num1 is not num2:
+                new_dist = euclidean_distance(point, point2)
+                if dists[num1] == None:
+                    dists[num1] = new_dist
+                elif dists[num1] > new_dist:
+                    dists[num1] = new_dist
+
+    return sum(dists)/len(points)
+
+def permutations(p=99, n=100, marks=None):
+    neighbor_perms = []
+    for i in range(p):
+        neighbor_perms.append(average_nearest_neighbor_distance(create_random_marked_points(n),
+            marks))
+    return neighbor_perms
+
+def compute_critical(perms):
+    return max(perms), min(perms)
+
+def check_significant(lower, upper, observed):
+    return(lower <= observed or observed <= upper)

io_geojson.py

@@ -0,0 +1,78 @@
+import json
+
+def read_geojson(input_file):
+    """
+    Read a geojson file
+
+    Parameters
+    ----------
+    input_file : str
+                 The PATH to the data to be read
+
+    Returns
+    -------
+    gj : dict
+         An in memory version of the geojson
+    """
+    # Please use the python json module (imported above)
+    # to solve this one.
+
+    with open(input_file, 'r') as f:
+        gj = json.load(f)
+    return gj
+
+
+def find_largest_city(gj):
+    """
+    Iterate through a geojson feature collection and
+    find the largest city.  Assume that the key
+    to access the maximum population is 'pop_max'.
+
+    Parameters
+    ----------
+    gj : dict
+         A GeoJSON file read in as a Python dictionary
+
+    Returns
+    -------
+    city : str
+           The largest city
+
+    population : int
+                 The population of the largest city
+    """
+    max_population = 0
+    city = None
+    features_list = gj.get('features')
+    x = 0
+
+    for f in features_list:
+        if f['properties']['pop_max'] > max_population:
+            max_population = f['properties']['pop_max']
+            city = f['properties']['name']
+
+    return city, max_population
+
+
+def write_your_own(gj):
+    """
+    Here you will write your own code to find
+    some attribute in the supplied geojson file.
+
+    Take a look at the attributes available and pick
+    something interesting that you might like to find
+    or summarize.  This is totally up to you.
+
+    Do not forget to write the accompanying test in
+    tests.py!
+    """
+    #find the largest city west of the Mississippi River
+
+    largest_western_city = None
+    features_list = gj.get('features')
+    for f in features_list:
+        if f['properties']['longitude'] < -95.202:
+            largest_western_city = f['properties']['longitude']
+
+
+    return largest_western_city

point.py

@@ -0,0 +1,111 @@
+import analytics
+import math
+import random
+import random
+import numpy as np
+
+
+class Point:
+
+    def __init__(self, x = 0, y = 0, mark = ''):
+        self.x = x
+        self.y = y
+        self.mark = mark
+
+    def __add__(self, other):
+        return Point(self.x + other.x, self.y + other.y)
+
+    def __eq__(self, other):
+        return self.x == other.x and self.y == other.y
+
+    def __radd__(self, other):
+        return Point(self.x + other, self.y + other)
+
+    def check_coincident(self, b):
+
+        if b.x == self.x and b.y == self.y:
+            return True
+
+    def shift_point(self, x_shift, y_shift):
+
+        self.x += x_shift
+        self.y += y_shift
+
+class PointPattern(object):
+
+    def __init__(self):
+        self.points = []
+        self.marks = []
+        self.length = len(self.points)
+
+    def __len__(self):
+        count = 0
+        for item in self.points:
+            count += 1
+        return count
+
+    def add_point(self, point):
+        self.points.append(point)
+
+    def remove_point(self, index):
+        del(self.points[index])
+
+    def average_nearest_neighor(self, mark=None):
+        return analytics.average_nearest_neighbor_distance(self.points, 
+                mark)
+
+    def count_coincident(self):
+        counted = []
+        count = 0
+        for index, point in enumerate(self.points):
+            for index2, point2 in enumerate(self.points):
+                if index != index2:
+                    if point.check_coincident(point2) is True:
+                        count += 1
+        return count
+
+    def list_marks(self):
+        marks = []
+        for point in self.points:
+            if point.mark not in marks and point.mark is not None:
+                marks.append(point.mark)
+        return marks
+
+    def points_by_mark(self, mark):
+
+        points_to_return = []
+        for point in self.points:
+            if point.mark == mark:
+                points_to_return.append(point)
+        return points_to_return
+
+    def generate_random_points(self, n = None, marks = None):
+
+        if n is None:
+            n = len(self.points)
+        point_list = analytics.create_random_marked_points(n, marks)
+        return point_list
+
+    def generate_realizations(p = 99, marks = None):
+        neighbor_perms = []
+        for i in range(p):
+            neighbor_perms.append(
+                    analytics.average_nearest_neighbor(
+                        generate_random_points()))
+        return neighbor_perms
+
+    def get_critical(neighbor_perms):
+        return max(perms), min(perms)
+
+    def comupte_g(self, nsteps):
+        ds = np.linspace(0, 1, nsteps)
+        dist_counts = []
+        for i, d in enumerate(ds):
+            min_dist = None
+            for n in range(nsteps):
+                if n != i:
+                    if min_dist is None or min_dist > d:
+                        min_dist = d
+            dist_counts.append(min_dist)
+        return sum(dist_counts)/nsteps
+