import pandas as pd

d = pd.read_csv('A2_mosquito_data.csv')
print d

import pandas as pd

data = pd.read_csv('A2_mosquito_data.csv')
print data.head()

data['temperature'] = (data['temperature'] - 32) * 5 / 9.0
print data.head()

import statsmodels.api as sm

regr_results = sm.OLS.from_formula('mosquitos ~ temperature + rainfall', data).fit()
regr_results.summary()

print regr_results.params
print regr_results.rsquared

parameters = regr_results.params
rsquared = regr_results.rsquared

%matplotlib inline

import matplotlib.pyplot as plt

predicted = parameters[0] + parameters[1] * data['temperature'] + parameters[2] * data['rainfall']
plt.plot(predicted, data['mosquitos'], 'ro')
min_mosquitos, max_mosquitos = min(data['mosquitos']), max(data['mosquitos'])
plt.plot([min_mosquitos, max_mosquitos], [min_mosquitos, max_mosquitos], 'k-')

import pandas as pd
import statsmodels.api as sm
import matplotlib.pyplot as plt

data = pd.read_csv('A2_mosquito_data.csv')
data['temperature'] = (data['temperature'] - 32) * 5 / 9.0
regr_results = sm.OLS.from_formula('mosquitos ~ temperature + rainfall', data).fit()
parameters = regr_results.params
rsquared = regr_results.rsquared
predicted = parameters[0] + parameters[1] * data['temperature'] + parameters[2] * data['rainfall']
plt.plot(predicted, data['mosquitos'], 'ro')
min_mosquitos, max_mosquitos = min(data['mosquitos']), max(data['mosquitos'])
plt.plot([min_mosquitos, max_mosquitos], [min_mosquitos, max_mosquitos], 'k-')
print parameters
print "R^2 = ", rsquared

def square(x):
    x_squared = x ** 2
    return x_squared

print "Four squared is", square(4)
print "Five squared is", square(5)

def square(x):
    return x ** 2

print square(3)

two_squared = square(2)
print two_squared

def fahr_to_celsius(tempF):
    tempC = (tempF - 32) * 5 / 9.0
    return tempC

original = 32.0
final = fahr_to_celsius(original)

print tempC

def center(data):
    return data - data.mean()

import pandas as pd

test_data = pd.DataFrame([[1, 1], [1, 2]])
print test_data

print center(test_data)

data = pd.read_csv('A2_mosquito_data.csv')
print center(data)

print 'original mean:'
print data.mean()
centered = center(data)
print
print 'mean of centered data:'
centered.mean()

print 'std dev before and after:'
print data.std()
print
print centered.std()

# center(data): return a new DataFrame containing the original data centered around zero.
def center(data, desired):
    return data - data.mean()

def center(data, desired):
    """Return a new DataFrame containing the original data centered around zero."""
    return data - data.mean()

help(center)

def center(data):
    """Return a new array containing the original data centered on zero
    
    Example:
    >>> import pandas
    >>> data = pandas.DataFrame([[0, 1], [0, 2])
    >>> center(data)
       0    1
    0  0 -0.5
    1  0  0.5

     
    """
    return data - data.mean()

help(center)

import pandas as pd
import statsmodels.api as sm
import matplotlib.pyplot as plt

def fahr_to_celsius(tempF):
    """Convert fahrenheit to celsius"""
    tempC = (tempF - 32) * 5 / 9.0
    return tempC

def analyze(data):
    """Perform regression analysis on mosquito data
    
    Takes a dataframe as input that includes columns named 'temperature',
    'rainfall', and 'mosquitos'.
    
    Performs a multiple regression to predict the number of mosquitos.
    Creates an observed-predicted plot of the result and
    returns the parameters of the regression.
    
    """
    regr_results = sm.OLS.from_formula('mosquitos ~ temperature + rainfall', data).fit()
    parameters = regr_results.params
    predicted = parameters[0] + parameters[1] * data['temperature'] + parameters[2] * data['rainfall']
    plt.figure()
    plt.plot(predicted, data['mosquitos'], 'ro')
    min_mosquitos, max_mosquitos = min(data['mosquitos']), max(data['mosquitos'])
    plt.plot([min_mosquitos, max_mosquitos], [min_mosquitos, max_mosquitos], 'k-')
    return parameters

data = pd.read_csv('A2_mosquito_data.csv')
data['temperature'] = fahr_to_celsius(data['temperature'])
regr_results = analyze(data)
print parameters

import glob

filenames = glob.glob('*.csv')
print filenames

mylist = [1, 'a', center]
print mylist

filenames =glob.glob('*data.csv')
for filename in filenames:
    print filename