import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
Run to view results
import pandas as pd
file_path = "/work/GROUP-1/API_FP.CPI.TOTL.ZG_DS2_en_csv_v2_32.csv"
df = pd.read_csv(file_path, skiprows=4)
print("Shape:", df.shape)
df.head()
Run to view results
df.columns
Run to view results
years = [str(year) for year in range(2014, 2025)]
columns_to_keep = ['Country Name', 'Country Code'] + years
df_recent = df[columns_to_keep]
df_recent.head()
Run to view results
df_recent = df_recent.dropna(thresh=8)
print("Shape after cleaning:", df_recent.shape)
Run to view results
plt.rcParams['figure.figsize'] = (10,5)
sns.set_style("whitegrid")
Run to view results
uae_yearly = pd.read_excel("/work/GROUP-1/CPI_Yearly_Index_2016_2020.xlsx")
Run to view results
uae_monthly = pd.read_excel(
"/work/GROUP-1/Consumer Price Index (CPI) - Monthly.xlsx",
header=4
)
Run to view results
uae_monthly = uae_monthly.drop(columns=[uae_monthly.columns[0], uae_monthly.columns[1]])
Run to view results
uae_monthly = uae_monthly.rename(columns={"Time period": "Date"})
Run to view results
uae_monthly["Date"] = pd.to_datetime(uae_monthly["Date"])
Run to view results
uae_monthly.head()
Run to view results
world_cpi = pd.read_csv(
"/work/GROUP-1/API_FP.CPI.TOTL.ZG_DS2_en_csv_v2_32.csv",
skiprows=4
)
Run to view results
# ================= FEATURE ENGINEERING =================
# ----- Monthly Dataset -----
uae_monthly["Year"] = uae_monthly["Date"].dt.year
uae_monthly["Month"] = uae_monthly["Date"].dt.month
uae_monthly["Quarter"] = uae_monthly["Date"].dt.quarter
uae_monthly["Inflation_Rate"] = uae_monthly["All Items"].pct_change() * 100
uae_monthly["CPI_Growth"] = uae_monthly["All Items"] - 100
uae_monthly["Rolling_3M_CPI"] = uae_monthly["All Items"].rolling(3).mean()
uae_monthly["Inflation_Direction"] = np.where(
uae_monthly["Inflation_Rate"] > 0,
"Increase",
"Decrease"
)
# ----- Yearly Dataset -----
uae_yearly["Year"] = uae_yearly["Date"].dt.year
# remove 2016
uae_yearly = uae_yearly[uae_yearly["Year"] >= 2017]
uae_yearly["Inflation_Rate"] = uae_yearly["All Items"].pct_change() * 100
uae_yearly["CPI_Growth"] = uae_yearly["All Items"] - 100
uae_yearly["Yearly_CPI_Change"] = uae_yearly["All Items"].diff()
# Preview
display(uae_monthly.head())
display(uae_yearly.head())
Run to view results
uae_monthly["Rolling_3M_CPI"] = uae_monthly["All Items"].rolling(3).mean()
Run to view results
uae_yearly["Yearly_CPI_Change"] = uae_yearly["All Items"].diff()
Run to view results
uae_monthly["Inflation_Direction"] = np.where(
uae_monthly["Inflation_Rate"] > 0,
"Increase",
"Decrease"
)
Run to view results
df_long = df_recent.melt(
id_vars=['Country Name', 'Country Code'],
value_vars=years,
var_name='Year',
value_name='Inflation'
)
df_long['Year'] = df_long['Year'].astype(int)
df_long = df_long.dropna()
df_long.head()
Run to view results
uae_monthly["Year"] = uae_monthly["Date"].dt.year
uae_monthly["Month"] = uae_monthly["Date"].dt.month
uae_monthly["Inflation"] = uae_monthly["All Items"].pct_change()*100
Run to view results
uae_yearly = uae_yearly[uae_yearly["Date"].dt.year >= 2017]
uae_yearly
Run to view results
plt.figure()
plt.plot(uae_monthly["Date"], uae_monthly["All Items"])
plt.title("UAE CPI Trend (2021–2025)")
plt.xlabel("Year")
plt.ylabel("CPI Index")
plt.text(
uae_monthly["Date"].iloc[5],
max(uae_monthly["All Items"]),
"Base Year = 2021 (Index = 100)",
fontsize=10
)
plt.show()
Run to view results
plt.figure(figsize=(10,5))
plt.plot(uae_yearly["Year"], uae_yearly["All Items"], marker="o", linewidth=2)
plt.title("UAE CPI Trend (2017–2020)")
plt.xlabel("Year")
plt.ylabel("CPI Index (Base Year = 2014 = 100)")
plt.xticks([2017, 2018, 2019, 2020])
plt.grid(True, linestyle="--", alpha=0.6)
plt.tight_layout()
plt.show()
Run to view results
plt.figure(figsize=(10,5))
plt.plot(uae_monthly["Date"], uae_monthly["Inflation"], color="orange")
plt.title("Monthly Inflation Rate in UAE (2021–2025)")
plt.xlabel("Year")
plt.ylabel("Inflation Rate (%)")
plt.grid(True, linestyle="--", alpha=0.6)
plt.show()
Run to view results
yearly_avg = uae_monthly.groupby("Year")["All Items"].mean()
plt.figure(figsize=(8,5))
yearly_avg.plot(kind="bar")
plt.title("Average CPI by Year (2021–2025)")
plt.ylabel("Average CPI")
plt.show()
Run to view results
import seaborn as sns
sns.histplot(uae_monthly["All Items"], kde=True)
plt.title("Distribution of CPI Values")
plt.show()
Run to view results
monthly_avg = uae_monthly.groupby("Month")["All Items"].mean()
plt.figure(figsize=(8,5))
monthly_avg.plot(kind="bar")
plt.title("Average CPI by Month")
plt.ylabel("Average CPI")
plt.show()
Run to view results
plt.figure(figsize=(10,5))
plt.plot(uae_monthly["Date"], uae_monthly["Food and Beverages"], label="Food")
plt.plot(uae_monthly["Date"], uae_monthly["Housing, Water, Electricity, Gas"], label="Housing")
plt.plot(uae_monthly["Date"], uae_monthly["Transportation"], label="Transport")
plt.legend()
plt.title("CPI Sector Comparison")
plt.xlabel("Year")
plt.ylabel("CPI Index")
plt.show()
Run to view results
plt.figure(figsize=(12,8))
corr = uae_monthly.select_dtypes(include='number').corr()
sns.heatmap(corr, cmap="coolwarm", annot=True)
plt.title("Correlation Between CPI Categories")
plt.show()
Run to view results
plt.figure(figsize=(8,5))
plt.plot(uae_yearly["Year"], uae_yearly["Inflation_Rate"], marker="o", color="orange")
plt.title("Yearly Inflation Rate in UAE (2017–2020)")
plt.xlabel("Year")
plt.ylabel("Inflation Rate (%)")
plt.xticks([2017, 2018, 2019, 2020])
plt.grid(True, linestyle="--", alpha=0.6)
plt.show()
Run to view results
plt.figure(figsize=(10,5))
plt.plot(uae_yearly["Year"], uae_yearly["Food and Beverages"], marker="o", label="Food")
plt.plot(uae_yearly["Year"], uae_yearly["Housing, Water, Electricity, Gas"], marker="o", label="Housing")
plt.plot(uae_yearly["Year"], uae_yearly["Transportation"], marker="o", label="Transport")
plt.legend()
plt.title("CPI Sector Trends in UAE (2017–2020)")
plt.xlabel("Year")
plt.ylabel("CPI Index")
plt.xticks([2017,2018,2019,2020])
plt.show()
Run to view results
sector_cols = [
"Food and Beverages",
"Housing, Water, Electricity, Gas",
"Transportation",
"Education",
"Restaurants and Hotels"
]
uae_yearly.set_index("Year")[sector_cols].plot(kind="bar", figsize=(10,5))
plt.title("Comparison of CPI Sectors in UAE (2017–2020)")
plt.ylabel("CPI Index")
plt.show()
Run to view results
import seaborn as sns
plt.figure(figsize=(10,8))
corr = uae_yearly.select_dtypes(include="number").corr()
sns.heatmap(corr, cmap="coolwarm")
plt.title("Correlation Between CPI Sectors (2017–2020)")
plt.show()
Run to view results
df_long = df_recent.melt(
id_vars=['Country Name', 'Country Code'],
value_vars=years,
var_name='Year',
value_name='Inflation'
)
df_long['Year'] = df_long['Year'].astype(int)
df_long = df_long.dropna()
df_long.head()
Run to view results
countries = ["United Arab Emirates","United States","China","India","Germany"]
subset = df_long[df_long["Country Name"].isin(countries)]
plt.figure(figsize=(10,5))
for c in countries:
data = subset[subset["Country Name"] == c]
plt.plot(data["Year"], data["Inflation"], label=c)
plt.legend()
plt.title("Inflation Comparison: UAE vs Major Economies")
plt.xlabel("Year")
plt.ylabel("Inflation Rate (%)")
plt.show()
Run to view results
latest = df_long[df_long["Year"] == df_long["Year"].max()]
top10 = latest.sort_values("Inflation", ascending=False).head(10)
plt.figure(figsize=(10,5))
plt.barh(top10["Country Name"], top10["Inflation"])
plt.title("Top 10 Countries with Highest Inflation")
plt.xlabel("Inflation Rate (%)")
plt.show()
Run to view results
bottom10 = latest.sort_values("Inflation").head(10)
plt.figure(figsize=(10,5))
plt.barh(bottom10["Country Name"], bottom10["Inflation"])
plt.title("Countries with Lowest Inflation")
plt.xlabel("Inflation Rate (%)")
plt.show()
Run to view results
top_countries = df_long.groupby("Country Name")["Inflation"].mean().sort_values(ascending=False).head(10).index
heat_data = df_long[df_long["Country Name"].isin(top_countries)]
heat_pivot = heat_data.pivot(index="Country Name", columns="Year", values="Inflation")
plt.figure(figsize=(12,6))
sns.heatmap(heat_pivot, cmap="coolwarm")
plt.title("Inflation Heatmap (Top Countries)")
plt.show()
Run to view results
inflation_std = df_long.groupby("Country Name")["Inflation"].std().sort_values(ascending=False).head(10)
plt.figure(figsize=(10,5))
inflation_std.plot(kind="bar")
plt.title("Countries with Most Volatile Inflation")
plt.ylabel("Inflation Standard Deviation")
plt.show()
Run to view results
plt.figure(figsize=(8,5))
plt.plot(uae_yearly["Year"], uae_yearly["All Items"], marker="o", label="UAE CPI")
plt.axvline(2018, color="red", linestyle="--", label="VAT Introduced")
plt.title("Impact of VAT Introduction on UAE CPI")
plt.xlabel("Year")
plt.ylabel("CPI Index (Base Year = 2014 = 100)")
plt.xticks([2017, 2018, 2019, 2020])
plt.legend()
plt.grid(True)
plt.show()
Run to view results
uae_global = df_long[df_long["Country Name"]=="United Arab Emirates"]
global_avg = df_long.groupby("Year")["Inflation"].mean()
plt.figure(figsize=(10,5))
plt.plot(global_avg.index, global_avg.values, label="Global Average")
plt.plot(uae_global["Year"], uae_global["Inflation"], label="UAE")
plt.axvline(2020,color="red",linestyle="--",label="COVID")
plt.legend()
plt.title("COVID-19 Impact on Inflation")
plt.xlabel("Year")
plt.ylabel("Inflation Rate (%)")
plt.show()
Run to view results
countries = ["United Arab Emirates","United States","India"]
subset = df_long[df_long["Country Name"].isin(countries)]
plt.figure(figsize=(10,5))
for c in countries:
d=subset[subset["Country Name"]==c]
plt.plot(d["Year"],d["Inflation"],label=c)
plt.axvline(2020,color="red",linestyle="--")
plt.legend()
plt.title("Impact of Oil Price Crash (2020)")
plt.xlabel("Year")
plt.ylabel("Inflation (%)")
plt.show()
Run to view results
global_avg = df_long.groupby("Year")["Inflation"].mean()
plt.figure(figsize=(10,5))
plt.plot(global_avg.index,global_avg.values)
plt.axvline(2021,color="red",linestyle="--",label="Suez Canal Blockage")
plt.title("Global Inflation and Supply Chain Disruptions")
plt.xlabel("Year")
plt.ylabel("Inflation (%)")
plt.legend()
plt.show()
Run to view results
plt.figure(figsize=(10,5))
plt.plot(uae_monthly["Date"],uae_monthly["Restaurants and Hotels"])
plt.axvspan(pd.to_datetime("2021-10-01"),
pd.to_datetime("2022-03-31"),
color="orange",alpha=0.3,label="Expo 2020")
plt.title("Impact of Expo 2020 on Hospitality Prices")
plt.xlabel("Year")
plt.ylabel("Hospitality CPI")
plt.legend()
plt.show()
Run to view results
plt.figure(figsize=(10,5))
plt.plot(global_avg.index,global_avg.values)
plt.axvline(2022,color="red",linestyle="--",label="Russia-Ukraine War")
plt.title("Global Inflation After the Russia-Ukraine War")
plt.xlabel("Year")
plt.ylabel("Inflation (%)")
plt.legend()
plt.show()
Run to view results
plt.figure(figsize=(10,5))
plt.plot(uae_monthly["Date"], uae_monthly["Food and Beverages"], label="UAE Food CPI")
# Event marker
plt.axvline(pd.to_datetime("2022-02-24"),
color="red",
linestyle="--",
label="Russia–Ukraine War Begins")
plt.title("Impact of Russia–Ukraine War on UAE Food Prices")
plt.xlabel("Year")
plt.ylabel("Food and Beverages CPI")
plt.legend()
plt.grid(True, linestyle="--", alpha=0.6)
plt.show()
Run to view results
plt.figure(figsize=(8,5))
plt.plot(uae_yearly["Year"], uae_yearly["All Items"], marker="o", label="UAE CPI")
plt.axvline(2018, color="red", linestyle="--", label="VAT Introduced")
plt.title("Impact of VAT Introduction on UAE CPI")
plt.xlabel("Year")
plt.ylabel("CPI Index (Base Year = 2014 = 100)")
plt.xticks([2017,2018,2019,2020])
plt.legend()
plt.grid(True, linestyle="--", alpha=0.6)
plt.show()
Run to view results
plt.figure(figsize=(10,5))
plt.plot(uae_yearly["Year"], uae_yearly["Food and Beverages"], marker="o", label="Food")
plt.plot(uae_yearly["Year"], uae_yearly["Transportation"], marker="o", label="Transport")
plt.plot(uae_yearly["Year"], uae_yearly["Restaurants and Hotels"], marker="o", label="Hospitality")
plt.axvline(2018, color="red", linestyle="--", label="VAT Introduced")
plt.title("Sector CPI Changes After VAT Introduction")
plt.xlabel("Year")
plt.ylabel("CPI Index")
plt.xticks([2017,2018,2019,2020])
plt.legend()
plt.grid(True, linestyle="--", alpha=0.6)
plt.show()
Run to view results
countries = ["United Arab Emirates","United States","Germany","India","United Kingdom"]
subset = df_long[df_long["Country Name"].isin(countries)]
plt.figure(figsize=(10,5))
for c in countries:
d = subset[subset["Country Name"]==c]
plt.plot(d["Year"], d["Inflation"], label=c)
plt.axvline(2022, color="red", linestyle="--", label="Global Inflation Surge")
plt.title("Inflation Stability: UAE vs Major Economies")
plt.xlabel("Year")
plt.ylabel("Inflation (%)")
plt.legend()
plt.grid(True)
plt.show()
Run to view results
plt.figure(figsize=(12,6))
# Plot UAE CPI trend
plt.plot(uae_monthly["Date"], uae_monthly["All Items"], label="UAE CPI", linewidth=2)
# Important events
events = {
"Suez Canal Blockage": "2021-03-23",
"Expo 2020": "2021-10-01",
"Russia-Ukraine War": "2022-02-24",
"Fed Rate Hike Cycle": "2022-03-16",
"Black Sea Grain Deal": "2022-07-22",
"El Niño": "2023-06-08",
"Panama Canal Drought": "2023-07-27",
"OPEC Production Cuts": "2023-11-30",
"Red Sea Shipping Disruptions": "2023-12-01"
}
# Add vertical lines for each event
for event, date in events.items():
plt.axvline(pd.to_datetime(date), linestyle="--", alpha=0.6)
plt.text(pd.to_datetime(date),
uae_monthly["All Items"].max(),
event,
rotation=90,
fontsize=8)
plt.title("UAE CPI Trend with Major Economic Events (2021–2025)")
plt.xlabel("Year")
plt.ylabel("CPI Index (2021 = 100)")
plt.legend()
plt.grid(True, linestyle="--", alpha=0.6)
plt.show()
Run to view results
plt.figure(figsize=(10,5))
plt.plot(uae_monthly["Date"], uae_monthly["Food and Beverages"])
plt.axvspan(pd.to_datetime("2022-07-22"),
pd.to_datetime("2023-07-17"),
color="green", alpha=0.3)
plt.title("Food Prices During Black Sea Grain Initiative")
plt.xlabel("Year")
plt.ylabel("Food CPI")
plt.show()
Run to view results
plt.figure(figsize=(10,5))
plt.plot(uae_monthly["Date"], uae_monthly["Food and Beverages"])
plt.axvline(pd.to_datetime("2023-06-08"), color="red", linestyle="--")
plt.title("Food Inflation Risk During El Niño")
plt.xlabel("Year")
plt.ylabel("Food CPI")
plt.show()
Run to view results
plt.figure(figsize=(10,5))
plt.plot(global_avg.index, global_avg.values)
plt.axvline(2023, color="red", linestyle="--")
plt.title("Global Inflation and Shipping Constraints")
plt.xlabel("Year")
plt.ylabel("Inflation (%)")
plt.show()
Run to view results
inflation_std = df_long.groupby("Country Name")["Inflation"].std()
uae_vol = inflation_std["United Arab Emirates"]
world_avg = inflation_std.mean()
print("UAE Inflation Volatility:", uae_vol)
print("Average Global Inflation Volatility:", world_avg)
Run to view results
uae = df_long[df_long["Country Name"]=="United Arab Emirates"]
global_avg = df_long.groupby("Year")["Inflation"].mean()
plt.figure(figsize=(10,5))
plt.plot(uae["Year"], uae["Inflation"], label="UAE")
plt.plot(global_avg.index, global_avg.values, label="Global Average")
plt.axvline(2020, color="red", linestyle="--", label="COVID Shock")
plt.title("Recovery of Inflation After COVID-19")
plt.xlabel("Year")
plt.ylabel("Inflation (%)")
plt.legend()
plt.grid(True)
plt.show()
Run to view results
categories = [
"Food and Beverages",
"Housing, Water, Electricity, Gas",
"Transportation",
"Restaurants and Hotels"
]
plt.figure(figsize=(10,5))
for c in categories:
plt.plot(uae_monthly["Date"], uae_monthly[c], label=c)
plt.axvline(pd.to_datetime("2022-02-24"), color="red", linestyle="--", label="Russia-Ukraine War")
plt.title("Key CPI Categories Driving Inflation in UAE")
plt.xlabel("Year")
plt.ylabel("CPI Index")
plt.legend()
plt.grid(True)
plt.show()
Run to view results
uae = df_long[df_long["Country Name"]=="United Arab Emirates"]
global_avg = df_long.groupby("Year")["Inflation"].mean()
plt.figure(figsize=(10,5))
plt.plot(uae["Year"], uae["Inflation"], label="UAE Inflation")
plt.plot(global_avg.index, global_avg.values, label="Global Average Inflation")
plt.title("UAE Inflation vs Global Average")
plt.xlabel("Year")
plt.ylabel("Inflation Rate (%)")
plt.legend()
plt.grid(True)
plt.show()
Run to view results
BY GROUP-1
SRI LAKSHMI PRAGHNA MANTHENA
AKANKSHA SWARNIM
AHMED YAKOUT
ABDALLAH YOUSSEF