#Importing relevant libraries for data analysis import pandas as pd import matplotlib.pyplot as plt import seaborn as sns

mining_data = pd.read_csv('MiningProcess_Flotation_Plant_Database.csv',decimal=',')

mining_data.head()

mining_data.shape

mining_data['% Iron Concentrate']

mining_data.iloc[100:105,:]

mining_data['date'] = pd.to_datetime(mining_data['date'])

print(type(mining_data['date'][0]))

mining_data.describe()

#finding the earliest and latest dates in the dataset, so see how long the data set spans for. mining_data['date'].min()

mining_data['date'].max()

#Making a dataframe for June time period df_june = mining_data[(mining_data['date'] > "2017-05-31 23:59:59") & (mining_data['date'] < "2017-06-02")].reset_index(drop=True)

df_june.head()

important_cols = [ 'date', '% Iron Concentrate', '% Silica Concentrate', 'Ore Pulp pH', 'Flotation Column 05 Level' ] df_june_important = df_june[important_cols] df_june_important

sns.pairplot(df_june_important)

df_june_important.corr()

sns.lineplot(x= 'date', y= '% Iron Concentrate', data= df_june_important)

import matplotlib.pyplot as plt for i in important_cols[1:]: graph = sns.lineplot(x='date', y=i, data= df_june_important) graph.set_xticklabels(graph.get_xticklabels(), rotation=40, ha="right") plt.show()