谷歌机器学习笔记之plt作图

# -*- coding: utf-8 -*-

from concurrent.futures  import ThreadPoolExecutor

import time
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np



datatmsp = pd.read_csv('california_housing_train.csv')

def process_features(data):
    data=data[
    ["latitude",
     "longitude",
     "housing_median_age",
     "total_rooms",
     "total_bedrooms",
     "population",
     "households",
     "median_income"]]

    processing =data.copy()
    processing["rooms_per_person"]=processing["total_rooms"]/processing["population"]
    return processing

def process_targets(data):
    processing=data.copy()
    processing=processing[["median_house_value"]]
    processing["median_house_value"]=processing["median_house_value"]/1000.0

    return processing




trainning_examples=process_features(datatmsp).head(12000)
print trainning_examples.describe()
trainning_targets=process_targets(datatmsp).head(12000)
print trainning_targets.describe()

valid_examples=process_features(datatmsp).tail(5000)
print valid_examples.describe()
valid_targets=process_targets(datatmsp).tail(5000)
print valid_targets.describe()


plt.figure(figsize=(13,8))
ax = plt.subplot(1, 2, 1)
ax.set_title("Validation Data")

ax.set_autoscaley_on(False)
ax.set_ylim([32, 43])
ax.set_autoscalex_on(False)
ax.set_xlim([-126, -112])
plt.scatter(valid_examples["longitude"],
            valid_examples["latitude"],
            cmap="coolwarm",
            c=valid_targets["median_house_value"] / valid_targets["median_house_value"].max())

ax = plt.subplot(1,2,2)
ax.set_title("Training Data")

ax.set_autoscaley_on(False)
ax.set_ylim([32, 43])
ax.set_autoscalex_on(False)
ax.set_xlim([-126, -112])
plt.scatter(trainning_examples["longitude"],
            trainning_examples["latitude"],
            cmap="coolwarm",
            c=trainning_targets["median_house_value"] / trainning_targets["median_house_value"].max())

plt.show()