import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt

df = pd.read_csv('C:/Users/eli/Desktop/application_record.csv')

# Recreate the Heatmap shown below
df = df.drop('FLAG_MOBIL', axis = 1)
sns.heatmap(df.corr(), annot = False, fmt='.1g',cmap= 'coolwarm')

fig, ax = plt.subplots(figsize=(10,8))  
np.round(df.corr(), 2)
sns.heatmap(np.round(df.corr(), 2), annot = True, linewidths=.5, ax=ax)
plt.show()

plt.figure(figsize=(12,8))
sns.heatmap(df.corr(),cmap='viridis', annot=True)

''' How are the worst movies rated across all platforms?
Create a clustermap visualiaztion of all normalized scores. Note the differences in ratings,
highly rated movies should be clustered together versus poorly rated movies. Note: this clustermap
does need to have the Film titles as the index, feel free to drop it for the clustermap.'''
g = sns.clustermap(df_norm_scores, cmap="mako", vmin=1, vmax=5, col_cluster = False)