# HIDDEN
# Clear previously defined variables
%reset -f

# Set directory for data loading to work properly
import os
os.chdir(os.path.expanduser('~/notebooks/17'))

# HIDDEN
import warnings
# Ignore numpy dtype warnings. These warnings are caused by an interaction
# between numpy and Cython and can be safely ignored.
# Reference: https://stackoverflow.com/a/40846742
warnings.filterwarnings("ignore", message="numpy.dtype size changed")
warnings.filterwarnings("ignore", message="numpy.ufunc size changed")

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
import seaborn as sns
%matplotlib inline
import ipywidgets as widgets
from ipywidgets import interact, interactive, fixed, interact_manual
import nbinteract as nbi

sns.set()
sns.set_context('talk')
np.set_printoptions(threshold=20, precision=2, suppress=True)
pd.options.display.max_rows = 7
pd.options.display.max_columns = 8
pd.set_option('precision', 2)
# This option stops scientific notation for pandas
# pd.set_option('display.float_format', '{:.2f}'.format)

# HIDDEN
def df_interact(df, nrows=7, ncols=7):
    '''
    Outputs sliders that show rows and columns of df
    '''
    def peek(row=0, col=0):
        return df.iloc[row:row + nrows, col:col + ncols]
    if len(df.columns) <= ncols:
        interact(peek, row=(0, len(df) - nrows, nrows), col=fixed(0))
    else:
        interact(peek,
                 row=(0, len(df) - nrows, nrows),
                 col=(0, len(df.columns) - ncols))
    print('({} rows, {} columns) total'.format(df.shape[0], df.shape[1]))

# HIDDEN
def jitter_df(df, x_col, y_col):
    x_jittered = df[x_col] + np.random.normal(scale=0, size=len(df))
    y_jittered = df[y_col] + np.random.normal(scale=0.05, size=len(df))
    return df.assign(**{x_col: x_jittered, y_col: y_jittered})

lebron = pd.read_csv('lebron.csv')
lebron

# HIDDEN
np.random.seed(42)
sns.lmplot(x='shot_distance', y='shot_made',
           data=jitter_df(lebron, 'shot_distance', 'shot_made'),
           fit_reg=False,
           scatter_kws={'alpha': 0.3})
plt.title('LeBron Shot Make vs. Shot Distance');

# HIDDEN
np.random.seed(42)
sns.lmplot(x='shot_distance', y='shot_made',
           data=jitter_df(lebron, 'shot_distance', 'shot_made'),
           ci=None,
           scatter_kws={'alpha': 0.4})
plt.title('Simple Linear Regression');

# HIDDEN
np.random.seed(42)
sns.lmplot(x='shot_distance', y='shot_made',
           data=jitter_df(lebron, 'shot_distance', 'shot_made'),
           ci=None,
           scatter_kws={'alpha': 0.4})
plt.axhline(y=0.5, linestyle='--', c='g')
plt.title('Cutoff for Classification');