linly/Mining-Away
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Yes

Browse Source
This commit is contained in:
Weaponised Autism
2023-03-30 18:22:32 +02:00
parent 172bcf3c23
commit 86107d5bb6
3 changed files with 11 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
py_scripts/engineer.py
View File

@@ -4,8 +4,6 @@ import seaborn as sns
import mining_hq
from numpy import count_nonzero
sns.set()
games_pre = mining_hq.games_sales_split_pre
games_dur = mining_hq.games_sales_split_dur
games_pos = mining_hq.games_sales_split_pos
@@ -13,6 +11,10 @@ games_pos = mining_hq.games_sales_split_pos
crime_US = mining_hq.crime_US_intersect
crime_CA = mining_hq.crime_CA_intersect
custom_params = {"axes.spines.right": False, "axes.spines.top": False}
sns.set_theme(style = 'ticks', rc = custom_params)
plt.xticks(rotation = 90)
games_fig_pre = sns.histplot(data = games_pre, x = "Year", palette = sns.color_palette("flare"), kde = True)
plt.show()
@@ -23,6 +25,8 @@ plt.show()
plt.xticks(rotation = 90)
games_fig_dur = sns.barplot(data = games_dur, x = "Year", y = "NA_Sales")
plt.xlabel("Years")
plt.ylabel("Sales in North America (Canada, USA)")
plt.show()
plt.xticks(rotation = 90)

15
py_scripts/mining_hq.py
View File

@@ -78,15 +78,6 @@ games_sales_split_dur = sale_tri_split[1]
games_sales_split_pos = sale_tri_split[2]
# Displaying Acquired Data
print("Acquired Datasets:\n")
print(sale_tri_split[0].head(5), sale_tri_split[1].head(5), sale_tri_split[2].head(5))
print("Dataset Info:\n")
sale_tri_split[0].info()
sale_tri_split[1].info()
sale_tri_split[2].info()
print("Dataset Info:\n")
games_sales_split_pre.info()
games_sales_split_dur.info()
@@ -113,8 +104,8 @@ gammas = digger.slam_dunk(gammas, "Critic_Score", labels=labels)
# Also need to transform using Z-score (normal distr go brrrr lmao), or min-max
# ah, scheiße
# nvm, done, kekW
gammas['Critic_Score'] = scout.scaling_zscore(gammas, 'Critic_Score')
print(gammas['Critic_Score'].head(10))
gammas['Critic_Score_Norm'] = scout.scaling_zscore(gammas, 'Critic_Score')
print(gammas['Critic_Score_Norm'].head(10))
# Saving all into a file
gammas.to_csv("output.csv", index=False)
@@ -125,4 +116,4 @@ chosen_idx = np.random.choice(len(gammas), replace = False, size = 5)
sample_rows = gammas.iloc[chosen_idx]
print(sample_rows.head())
scout.dissimilarity(sample_rows.select_dtypes(include = np.number))
# scout.dissimilarity(sample_rows.select_dtypes(include = np.number))